messages listlengths 2 2 | correct_answer stringclasses 2
values | paper_a_rating float64 1 10 | paper_b_rating float64 1 10 | paper_a_title stringlengths 8 179 | paper_b_title stringlengths 8 179 | year int64 2.02k 2.03k | paper_a_abstract stringlengths 1 5k | paper_b_abstract stringlengths 1 5k |
|---|---|---|---|---|---|---|---|---|
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 8.333333 | 8 | Discrete Variational Autoencoders | The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables | 2,017 | Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete late... | The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random variable with fixed distribution. After refactoring, the gradients of the loss propag... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 6 | 7.333333 | Introducing Active Learning for CNN under the light of Variational Inference | Sigma Delta Quantized Networks | 2,017 | One main concern of the deep learning community is to increase the capacity of
representation of deep networks by increasing their depth. This requires to scale
up the size of the training database accordingly. Indeed a major intuition lies in
the fact that the depth of the network and the size of the training set are ... | Deep neural networks can be obscenely wasteful. When processing video, a convolutional network expends a fixed amount of computation for each frame with no regard to the similarity between neighbouring frames. As a result, it ends up repeatedly doing very similar computations. To put an end to such waste, we introduce ... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 5.333333 | 5 | Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders | Revisiting Batch Normalization For Practical Domain Adaptation | 2,017 | We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself i... | Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific doma... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 5.666667 | 5.333333 | Adversarial examples in the physical world | Boosted Generative Models | 2,017 | Most existing machine learning classifiers are highly vulnerable to adversarial examples.
An adversarial example is a sample of input data which has been modified
very slightly in a way that is intended to cause a machine learning classifier
to misclassify it.
In many cases, these modifications can be so subtle that a ... | We propose a new approach for using boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our algorithm can leverage many existing base learners, including recent latent variable models. Further, our approach allows the ensemble to leverage discriminativ... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 5.333333 | 3.666667 | Extrapolation and learning equations | Multi-modal Variational Encoder-Decoders | 2,017 | In classical machine learning, regression is treated as a black box process of identifying a
suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs.
In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goa... | Recent advances in neural variational inference have facilitated efficient training of powerful directed graphical models with continuous latent variables, such as variational autoencoders. However, these models usually assume simple, uni-modal priors — such as the multivariate Gaussian distribution — yet many real-wor... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 4.666667 | 3.666667 | Transformation-based Models of Video Sequences | Rule Mining in Feature Space | 2,017 | In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a sequence, given the transformations of the past frames. This leads to sharper result... | Relational embeddings have emerged as an excellent tool for inferring novel facts
from partially observed knowledge bases. Recently, it was shown that some
classes of embeddings can also be exploited to perform a simplified form of rule
mining. By interpreting logical conjunction as a form of composition between re-
la... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 7 | 4.333333 | Do Deep Convolutional Nets Really Need to be Deep and Convolutional? | Local minima in training of deep networks | 2,017 | Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-f... | There has been a lot of recent interest in trying to characterize the error surface of deep models. This stems from a long standing question. Given that deep networks are highly nonlinear systems optimized by local gradient methods, why do they not seem to be affected by bad local minima? It is widely believed that tra... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 5 | 6 | Adding Gradient Noise Improves Learning for Very Deep Networks | Unsupervised Pretraining for Sequence to Sequence Learning | 2,017 | Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. Recently, more complex architectures such as Neural Turing Machines and Memory Networks have been proposed for tasks including question answering and general computation, creating a new set... | This work presents a general unsupervised learning method to improve
the accuracy of sequence to sequence (seq2seq) models. In our method, the
weights of the encoder and decoder of a seq2seq model are initialized
with the pretrained weights of two language models and then
fine-tuned with labeled data. We apply this me... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 2.666667 | 6 | Learning similarity preserving representations with neural similarity and context encoders | FractalNet: Ultra-Deep Neural Networks without Residuals | 2,017 | We introduce similarity encoders (SimEc), which learn similarity preserving representations by using a feed-forward neural network to map data into an embedding space where the original similarities can be approximated linearly. The model can easily compute representations for novel (out-of-sample) data points, even if... | We introduce a design strategy for neural network macro-architecture based on self-similarity. Repeated application of a simple expansion rule generates deep networks whose structural layouts are precisely truncated fractals. These networks contain interacting subpaths of different lengths, but do not include any pas... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 7 | 4.666667 | Highway and Residual Networks learn Unrolled Iterative Estimation | Sequence to Sequence Transduction with Hard Monotonic Attention | 2,017 | The past year saw the introduction of new architectures such as Highway networks and Residual networks which, for the first time, enabled the training of feedforward networks with dozens to hundreds of layers using simple gradient descent.
While depth of representation has been posited as a primary reason for their suc... | We present a supervised sequence to sequence transduction model with a hard attention mechanism which combines the more traditional statistical alignment methods with the power of recurrent neural networks. We evaluate the model on the task of morphological inflection generation and show that it provides state of the a... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 4.333333 | 8.333333 | Improving Invariance and Equivariance Properties of Convolutional Neural Networks | Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data | 2,017 | Convolutional Neural Networks (CNNs) learn highly discriminative representations from data, but how robust and structured are these representations? How does the data shape the internal network representation? We shed light on these questions by empirically measuring the invariance and equivariance properties of a larg... | Some machine learning applications involve training data that is sensitive, such
as the medical histories of patients in a clinical trial. A model may
inadvertently and implicitly store some of its training data; careful analysis
of the model may therefore reveal sensitive information.
To address this problem, we demo... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 7 | 6.666667 | Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling | Stick-Breaking Variational Autoencoders | 2,017 | Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against one-hot targets, and each word is represented both as an input and as an output in ... | We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesian nonparametric version of the variational autoencoder that has a latent representation with stocha... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 9 | 7.333333 | Neural Architecture Search with Reinforcement Learning | Revisiting Classifier Two-Sample Tests | 2,017 | Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and trai... | The goal of two-sample tests is to assess whether two samples, $S_P \sim P^n$ and $S_Q \sim Q^m$, are drawn from the same distribution. Perhaps intriguingly, one relatively unexplored method to build two-sample tests is the use of binary classifiers. In particular, construct a dataset by pairing the $n$ examples in $S... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 3.333333 | 8 | Learning to Understand: Incorporating Local Contexts with Global Attention for Sentiment Classification | On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima | 2,017 | Recurrent neural networks have shown their ability to construct sentence or paragraph representations. Variants such as LSTM overcome the problem of vanishing gradients to some degree, thus being able to model long-time dependency. Still, these recurrent based models lack the ability of capturing complex semantic compo... | The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$--$512$ data points, is sampled to compute an approximation to the gradient. It has been observed in practi... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 5.333333 | 5 | Sampling Generative Networks | Recursive Regression with Neural Networks: Approximating the HJI PDE Solution | 2,017 | We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces sharper samples. J-Diagrams and MINE grids are introduced as visualizations of manifol... | Most machine learning applications using neural networks seek to approximate some function g(x) by minimizing some cost criterion. In the simplest case, if one has access to pairs of the form (x, y) where y = g(x), the problem can be framed as a regression problem. Beyond this family of problems, we find many cases whe... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 7 | 6.666667 | Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain | Generative Multi-Adversarial Networks | 2,017 | Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent should be able to avoid negative transfer, which happens when the transfer hampe... | Generative adversarial networks (GANs) are a framework for producing a generative model by way of a two-player minimax game. In this paper, we propose the \emph{Generative Multi-Adversarial Network} (GMAN), a framework that extends GANs to multiple discriminators. In previous work, the successful training of GANs requ... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 6.333333 | 7 | Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning | Learning in Implicit Generative Models | 2,017 | People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algor... | Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they provide samples that are sharp and compelling; and they allow us to harness our knowl... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 6.666667 | 7 | Optimal Binary Autoencoding with Pairwise Correlations | Loss-aware Binarization of Deep Networks | 2,017 | We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the autoencoder that reconstructs its inputs with worst-case optimal loss. The optimal decode... | Deep neural network models, though very powerful and highly successful, are computationally expensive in terms of space and time. Recently, there have been a number of attempts on binarizing the network weights and activations. This greatly reduces the network size, and replaces the underlying multiplications to additi... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 9.666667 | 4.333333 | Understanding deep learning requires rethinking generalization | Charged Point Normalization: An Efficient Solution to the Saddle Point Problem | 2,017 | Despite their massive size, successful deep artificial neural networks can
exhibit a remarkably small difference between training and test performance.
Conventional wisdom attributes small generalization error either to properties
of the model family, or to the regularization techniques used during training.
Through e... | Recently, the problem of local minima in very high dimensional non-convex optimization has been challenged and the problem of saddle points has been introduced. This paper introduces a dynamic type of normalization that forces the system to escape saddle points. Unlike other saddle point escaping algorithms, second ord... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 7.333333 | 4.666667 | Latent Sequence Decompositions | Multiplicative LSTM for sequence modelling | 2,017 | Sequence-to-sequence models rely on a fixed decomposition of the target sequences into a sequence of tokens that may be words, word-pieces or characters. The choice of these tokens and the decomposition of the target sequences into a sequence of tokens is often static, and independent of the input, output data domains.... | We introduce multiplicative LSTM (mLSTM), a novel recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures. mLSTM is characterised by its ability to have different recurrent transition functions for each possib... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 6.666667 | 3.666667 | Efficient Softmax Approximation for GPUs | Rule Mining in Feature Space | 2,017 | We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the unbalanced word distribution to form clusters that explicitly minimize the expectat... | Relational embeddings have emerged as an excellent tool for inferring novel facts
from partially observed knowledge bases. Recently, it was shown that some
classes of embeddings can also be exploited to perform a simplified form of rule
mining. By interpreting logical conjunction as a form of composition between re-
la... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 3.333333 | 7 | Boosted Residual Networks | DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning | 2,017 | In this paper we present a new ensemble method, called Boosted Residual Networks,
which builds an ensemble of Residual Networks by growing the member
network at each round of boosting. The proposed approach combines recent developements
in Residual Networks - a method for creating very deep networks by
including a shor... | In recent years, Deep Learning (DL) has found great success in domains such as multimedia understanding. However, the complex nature of multimedia data makes it difficult to develop DL-based software. The state-of-the-art tools, such as Caffe, TensorFlow, Torch7, and CNTK, while are successful in their applicable domai... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 6.333333 | 4 | Intelligible Language Modeling with Input Switched Affine Networks | A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games | 2,017 | The computational mechanisms by which nonlinear recurrent neural networks (RNNs) achieve their goals remains an open question. There exist many problem domains where intelligibility of the network model is crucial for deployment. Here we introduce a recurrent architecture composed of input-switched affine transformati... | Reinforcement learning is concerned with learning to interact with environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as DQN, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts of data. Model-based ... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 4 | 5 | Simple Black-Box Adversarial Perturbations for Deep Networks | Recursive Regression with Neural Networks: Approximating the HJI PDE Solution | 2,017 | Deep neural networks are powerful and popular learning models that achieve state-of-the-art pattern recognition performance on many computer vision, speech, and language processing tasks. However, these networks have also been shown susceptible to carefully crafted adversarial perturbations which force misclassificatio... | Most machine learning applications using neural networks seek to approximate some function g(x) by minimizing some cost criterion. In the simplest case, if one has access to pairs of the form (x, y) where y = g(x), the problem can be framed as a regression problem. Beyond this family of problems, we find many cases whe... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 4.666667 | 6.333333 | Towards Information-Seeking Agents | Recurrent Mixture Density Network for Spatiotemporal Visual Attention | 2,017 | We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed environment, for fragments of information which can be pieced together to accomplish vari... | In many computer vision tasks, the relevant information to solve the problem at hand is mixed to irrelevant, distracting information. This has motivated researchers to design attentional models that can dynamically focus on parts of images or videos that are salient, e.g., by down-weighting irrelevant pixels. In this w... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 4.333333 | 6.666667 | Generalizable Features From Unsupervised Learning | Learning to Query, Reason, and Answer Questions On Ambiguous Texts | 2,017 | Humans learn a predictive model of the world and use this model to reason about future events and the consequences of actions. In contrast to most machine predictors, we exhibit an impressive ability to generalize to unseen scenarios and reason intelligently in these settings. One important aspect of this ability is p... | A key goal of research in conversational systems is to train an interactive agent to help a user with a task. Human conversation, however, is notoriously incomplete, ambiguous, and full of extraneous detail. To operate effectively, the agent must not only understand what was explicitly conveyed but also be able to reas... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 6.333333 | 7.75 | Paleo: A Performance Model for Deep Neural Networks | Metacontrol for Adaptive Imagination-Based Optimization | 2,017 | Although various scalable deep learning software packages have been proposed, it remains unclear how to best leverage parallel and distributed computing infrastructure to accelerate their training and deployment. Moreover, the effectiveness of existing parallel and distributed systems varies widely based on the neural ... | Many machine learning systems are built to solve the hardest examples of a particular task, which often makes them large and expensive to run---especially with respect to the easier examples, which might require much less computation. For an agent with a limited computational budget, this "one-size-fits-all" approach m... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 7 | 8.333333 | Batch Policy Gradient Methods for Improving Neural Conversation Models | Deep Information Propagation | 2,017 | We study reinforcement learning of chat-bots with recurrent neural network
architectures when the rewards are noisy and expensive to
obtain. For instance, a chat-bot used in automated customer service support can
be scored by quality assurance agents, but this process can be expensive, time consuming
and noisy.
Previo... | We study the behavior of untrained neural networks whose weights and biases are randomly distributed using mean field theory. We show the existence of depth scales that naturally limit the maximum depth of signal propagation through these random networks. Our main practical result is to show that random networks may be... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 5.666667 | 5.333333 | FastText.zip: Compressing text classification models | Regularizing Neural Networks by Penalizing Confident Output Distributions | 2,017 | We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store the word embeddings. While the origina... | We propose regularizing neural networks by penalizing low entropy output distributions. We show that penalizing low entropy output distributions, which has been shown to improve exploration in reinforcement learning, acts as a strong regularizer in supervised learning. We connect our confidence penalty to label smoothi... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 5.333333 | 7.666667 | Classless Association using Neural Networks | Combining policy gradient and Q-learning | 2,017 | The goal of this paper is to train a model based on the relation between two instances that represent the same unknown class. This scenario is inspired by the Symbol Grounding Problem and the association learning in infants. We propose a novel model called Classless Association. It has two parallel Multilayer Percep... | Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experie... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 6 | 5.666667 | Delving into Transferable Adversarial Examples and Black-box Attacks | Revisiting Distributed Synchronous SGD | 2,017 | An intriguing property of deep neural networks is the existence of adversarial examples, which can transfer among different architectures. These transferable adversarial examples may severely hinder deep neural network-based applications. Previous works mostly study the transferability using small scale datasets. In th... | Distributed training of deep learning models on large-scale training data is typically conducted with asynchronous stochastic optimization to maximize the rate of updates, at the cost of additional noise introduced from asynchrony. In contrast, the synchronous approach is often thought to be impractical due to idle tim... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 6.666667 | 4.333333 | Hadamard Product for Low-rank Bilinear Pooling | Shift Aggregate Extract Networks | 2,017 | Bilinear models provide rich representations compared with linear models. They have been applied in various visual tasks, such as object recognition, segmentation, and visual question-answering, to get state-of-the-art performances taking advantage of the expanded representations. However, bilinear representations tend... | The Shift Aggregate Extract Network SAEN is an architecture for learning representations on social network data.
SAEN decomposes input graphs into hierarchies made of multiple strata of objects.
Vector representations of each object are learnt by applying 'shift', 'aggregate' and 'extract' operations on the vector repr... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 5.666667 | 4.666667 | Emergence of foveal image sampling from learning to attend in visual scenes | Multiplicative LSTM for sequence modelling | 2,017 | We describe a neural attention model with a learnable retinal sampling lattice. The model is trained on a visual search task requiring the classification of an object embedded in a visual scene amidst background distractors using the smallest number of fixations. We explore the tiling properties that emerge in the mode... | We introduce multiplicative LSTM (mLSTM), a novel recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures. mLSTM is characterised by its ability to have different recurrent transition functions for each possib... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 4.8 | 6.5 | Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability | Exploring Sparsity in Recurrent Neural Networks | 2,017 | Tartan {TRT} a hardware accelerator for inference with Deep Neural Networks (DNNs) is presented and evaluated on Convolutional Neural Networks. TRT exploits the variable per layer precision requirements of DNNs to deliver execution time that is proportional to the precision p in bits used per layer for convolutional an... | Recurrent neural networks (RNN) are widely used to solve a variety of problems and as the quantity of data and the amount of available compute have increased, so have model sizes. The number of parameters in recent state-of-the-art networks makes them hard to deploy, especially on mobile phones and embedded devices. Th... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 8.333333 | 4.666667 | Making Neural Programming Architectures Generalize via Recursion | Hierarchical Memory Networks | 2,017 | Empirically, neural networks that attempt to learn programs from data have exhibited poor generalizability. Moreover, it has traditionally been difficult to reason about the behavior of these models beyond a certain level of input complexity. In order to address these issues, we propose augmenting neural architectures ... | Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which ... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 7.333333 | 5.333333 | Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening | Unsupervised Perceptual Rewards for Imitation Learning | 2,017 | We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the trainin... | Reward function design and exploration time are arguably the biggest obstacles to the deployment of reinforcement learning (RL) agents in the real world. In many real-world tasks, designing a suitable reward function takes considerable manual engineering and often requires additional and potentially visible sensors to ... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | A | 7.333333 | 7 | Pruning Convolutional Neural Networks for Resource Efficient Inference | Loss-aware Binarization of Deep Networks | 2,017 | We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation-a computationally efficient procedure that maintains good generalization in the pruned network. We propose a new criterion base... | Deep neural network models, though very powerful and highly successful, are computationally expensive in terms of space and time. Recently, there have been a number of attempts on binarizing the network weights and activations. This greatly reduces the network size, and replaces the underlying multiplications to additi... |
[
{
"role": "system",
"content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."
},
{
"role": "user",
"content": "Based on the titles and abstracts of the following two papers A and B submitted to ICLR 2017, determi... | B | 5.333333 | 5.5 | Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders | Parametric Exponential Linear Unit for Deep Convolutional Neural Networks | 2,017 | We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself i... | The activation function is an important component in Convolutional Neural Networks (CNNs). For instance, recent breakthroughs in Deep Learning can be attributed to the Rectified Linear Unit (ReLU). Another recently proposed activation function, the Exponential Linear Unit (ELU), has the supplementary property of reduci... |
End of preview. Expand in Data Studio
No dataset card yet
- Downloads last month
- 26