Publications

Measuring the tendency of CNNs to Learn Surface Statistical Regularities

Jason Jo

Deep CNNs are known to exhibit the following peculiarity: on the one hand they generalize extremely well to a test set, while on the other h… (see more)and they are extremely sensitive to so-called adversarial perturbations. The extreme sensitivity of high performance CNNs to adversarial examples casts serious doubt that these networks are learning high level abstractions in the dataset. We are concerned with the following question: How can a deep CNN that does not learn any high level semantics of the dataset manage to generalize so well? The goal of this article is to measure the tendency of CNNs to learn surface statistical regularities of the dataset. To this end, we use Fourier filtering to construct datasets which share the exact same high level abstractions but exhibit qualitatively different surface statistical regularities. For the SVHN and CIFAR-10 datasets, we present two Fourier filtered variants: a low frequency variant and a randomly filtered variant. Each of the Fourier filtering schemes is tuned to preserve the recognizability of the objects. Our main finding is that CNNs exhibit a tendency to latch onto the Fourier image statistics of the training dataset, sometimes exhibiting up to a 28% generalization gap across the various test sets. Moreover, we observe that significantly increasing the depth of a network has a very marginal impact on closing the aforementioned generalization gap. Thus we provide quantitative evidence supporting the hypothesis that deep CNNs tend to learn surface statistical regularities in the dataset rather than higher-level abstract concepts.

2017-11-29

ArXiv (preprint)

Ubenwa: Cry-based Diagnosis of Birth Asphyxia

Charles Onu

Innocent Udeogu

Eyenimi Ndiomu

Urbain Kengni

Doina Precup

Guilherme M. Sant’Anna

E. Alikor

P. Opara

Every year, 3 million newborns die within the first month of life. Birth asphyxia and other breathing-related conditions are a leading cause… (see more) of mortality during the neonatal phase. Current diagnostic methods are too sophisticated in terms of equipment, required expertise, and general logistics. Consequently, early detection of asphyxia in newborns is very difficult in many parts of the world, especially in resource-poor settings. We are developing a machine learning system, dubbed Ubenwa, which enables diagnosis of asphyxia through automated analysis of the infant cry. Deployed via smartphone and wearable technology, Ubenwa will drastically reduce the time, cost and skill required to make accurate and potentially life-saving diagnoses.

2017-11-16

ArXiv (preprint)

Design of a Recognition System Automatic Vehicle License Plate through a Convolution Neural Network

P. Rajendra

K. Sudheer

Rahul Boadh

TE Campos

BR Babu

M. Varma

Ian J Goodfellow

Aaron

The present work is a study on the practical application of Learning process (Deep Learning) in the development of a system of Automatic rec… (see more)ognition of vehicle license plates. These systems commonly referred to as ALPR (Automatic License Plate Recognition) - are able to recognize the content of vehicles from the images captured by a camera. The system proposed in this work is based on an image classifier developed through supervised learning techniques with convolution neural network. These networks are one of the most profound learning architectures and are specifically designed to solve artificial vision, such as pattern recognition and classification of images. This paper also examines basic processing techniques and Image segmentation - such as smoothing filters, contour detection - necessary for the proposed system to be able to extract the contents of the license plates for further analysis and classification. This paper demonstrates the feasibility of an ALPR system based on a convolution neural network, noting the critical importance it has to design a network architecture and training data set appropriate to the problem to be solved.

2017-11-14

International Journal of Computer Applications (published)

Variational Bi-LSTMs

Samira Shabanian

Devansh Arpit

Adam Trischler

Recurrent neural networks like long short-term memory (LSTM) are important architectures for sequential prediction tasks. LSTMs (and RNNs in… (see more) general) model sequences along the forward time direction. Bidirectional LSTMs (Bi-LSTMs), which model sequences along both forward and backward directions, generally perform better at such tasks because they capture a richer representation of the data. In the training of Bi-LSTMs, the forward and backward paths are learned independently. We propose a variant of the Bi-LSTM architecture, which we call Variational Bi-LSTM, that creates a dependence between the two paths (during training, but which may be omitted during inference). Our model acts as a regularizer and encourages the two networks to inform each other in making their respective predictions using distinct information. We perform ablation studies to better understand the different components of our model and evaluate the method on various benchmarks, showing state-of-the-art performance.

2017-11-14

ArXiv (preprint)

Actual: Actor-Critic Under Adversarial Learning

Nan Rosemary Ke

R Devon Hjelm

Generative Adversarial Networks (GANs) are a powerful framework for deep generative modeling. Posed as a two-player minimax problem, GANs ar… (see more)e typically trained end-to-end on real-valued data and can be used to train a generator of high-dimensional and realistic images. However, a major limitation of GANs is that training relies on passing gradients from the discriminator through the generator via back-propagation. This makes it fundamentally difficult to train GANs with discrete data, as generation in this case typically involves a non-differentiable function. These difficulties extend to the reinforcement learning setting when the action space is composed of discrete decisions. We address these issues by reframing the GAN framework so that the generator is no longer trained using gradients through the discriminator, but is instead trained using a learned critic in the actor-critic framework with a Temporal Difference (TD) objective. This is a natural fit for sequence modeling and we use it to achieve improvements on language modeling tasks over the standard Teacher-Forcing methods.

2017-11-12

ArXiv (preprint)

Three Factors Influencing Minima in SGD

Stanisław Jastrzębski

Amos Storkey

We study the statistical properties of the endpoint of stochastic gradient descent (SGD). We approximate SGD as a stochastic differential eq… (see more)uation (SDE) and consider its Boltzmann Gibbs equilibrium distribution under the assumption of isotropic variance in loss gradients.. Through this analysis, we find that three factors – learning rate, batch size and the variance of the loss gradients – control the trade-off between the depth and width of the minima found by SGD, with wider minima favoured by a higher ratio of learning rate to batch size. In the equilibrium distribution only the ratio of learning rate to batch size appears, implying that it’s invariant under a simultaneous rescaling of each by the same amount. We experimentally show how learning rate and batch size affect SGD from two perspectives: the endpoint of SGD and the dynamics that lead up to it. For the endpoint, the experiments suggest the endpoint of SGD is similar under simultaneous rescaling of batch size and learning rate, and also that a higher ratio leads to flatter minima, both findings are consistent with our theoretical analysis. We note experimentally that the dynamics also seem to be similar under the same rescaling of learning rate and batch size, which we explore showing that one can exchange batch size and learning rate in a cyclical learning rate schedule. Next, we illustrate how noise affects memorization, showing that high noise levels lead to better generalization. Finally, we find experimentally that the similarity under simultaneous rescaling of learning rate and batch size breaks down if the learning rate gets too large or the batch size gets too small.

2017-11-12

ArXiv (preprint)

openreview.net

Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks

Nan Rosemary Ke

A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagat… (see more)e credit information backwards through every single step of the forward computation. This makes BPTT both computationally impractical and biologically implausible. For this reason, full backpropagation through time is rarely used on long sequences, and truncated backpropagation through time is used as a heuristic. However, this usually leads to biased estimates of the gradient in which longer term dependencies are ignored. Addressing this issue, we propose an alternative algorithm, Sparse Attentive Backtracking, which might also be related to principles used by brains to learn long-term dependencies. Sparse Attentive Backtracking learns an attention mechanism over the hidden states of the past and selectively backpropagates through paths with high attention weights. This allows the model to learn long term dependencies while only backtracking for a small number of time steps, not just from the recent past but also from attended relevant past states.

2017-11-06

ArXiv (preprint)

openreview.net

Fast and Flexible Successive-Cancellation List Decoders for Polar Codes

Seyyed Ali Hashemi

Carlo Condo

Warren J. Gross

Polar codes have gained significant amount of attention during the past few years and have been selected as a coding scheme for the next gen… (see more)eration of mobile broadband standard. Among decoding schemes, successive-cancellation list (SCL) decoding provides a reasonable tradeoff between the error-correction performance and hardware implementation complexity when used to decode polar codes, at the cost of limited throughput. The simplified SCL (SSCL) and its extension SSCL-SPC increase the speed of decoding by removing redundant calculations when encountering particular information and frozen bit patterns (rate one and single parity check codes), while keeping the error-correction performance unaltered. In this paper, we improve SSCL and SSCL-SPC by proving that the list size imposes a specific number of path splitting required to decode rate one and single parity check codes. Thus, the number of splitting can be limited while guaranteeing exactly the same error-correction performance as if the paths were forked at each bit estimation. We call the new decoding algorithms Fast-SSCL and Fast-SSCL-SPC. Moreover, we show that the number of path forks in a practical application can be tuned to achieve desirable speed, while keeping the error-correction performance almost unchanged. Hardware architectures implementing both algorithms are then described and implemented: It is shown that our design can achieve

2017-10-31

IEEE Transactions on Signal Processing (published)

Graph Attention Networks

Petar Veličković

Guillem Cucurull

Arantxa Casanova

Adriana Romero

Pietro Lio

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self… (see more)-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).

2017-10-29

ArXiv (preprint)

openreview.net

Automatic Differentiation in Myia

Olivier Breuleux

Bart Van Merriënboer

Automatic differentiation is an essential feature of machine learning frameworks. However, its implementation in existing frameworks often h… (see more)as limitations. In dataflow programming frameworks such as Theano or TensorFlow the representation used makes supporting higher-order gradients difficult. On the other hand, operator overloading frameworks such as PyTorch are flexible, but do not lend themselves well to optimization. With Myia, we attempt to have the best of both worlds: Building on the work by Pearlmutter and Siskind we implement a first-order gradient operator for a subset of the Python programming language.

2017-10-27

(published)

www.semanticscholar.org

An empirical study on aggregation of alternatives and its influence on prediction in car type choice models

Shiva Habibi

Emma Frejinger

M. Sundberg

2017-10-26

Transportation (published)