deep learning

Kernel Methods for Deep Learning

Neural Information Processing Systems

We introduce a new family of positive-definite kernel functions that mimic the computation in large, multilayer neural nets. These kernel functions can be used in shallow architectures, such as support vector machines (SVMs), or in deep kernel-based architectures that we call multilayer kernel machines (MKMs). We evaluate SVMs and MKMs with these kernel functions on problems designed to illustrate the advantages of deep architectures. On several problems, we obtain better results than previous, leading benchmarks from both SVMs with Gaussian kernels as well as deep belief nets. Papers published at the Neural Information Processing Systems Conference.

Image Denoising and Inpainting with Deep Neural Networks

Neural Information Processing Systems

We present a novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA). We propose an alternative training scheme that successfully adapts DA, originally designed for unsupervised feature learning, to the tasks of image denoising and blind inpainting. Our method achieves state-of-the-art performance in the image denoising task. More importantly, in blind image inpainting task, the proposed method provides solutions to some complex problems that have not been tackled before. Specifically, we can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random.

The 10 Best Examples Of How Companies Use Artificial Intelligence In Practice


All the world's tech giants from Alibaba to Amazon are in a race to become the world's leaders in artificial intelligence (AI). These companies are AI trailblazers and embrace AI to provide next-level products and services. Here are 10 of the best examples of how these companies are using artificial intelligence in practice. Chinese company Alibaba is the world's largest e-commerce platform that sells more than Amazon and eBay combined. Artificial intelligence (AI) is integral in Alibaba's daily operations and is used to predict what customers might want to buy.

Surround Modulation: A Bio-inspired Connectivity Structure for Convolutional Neural Networks

Neural Information Processing Systems

Numerous neurophysiological studies have revealed that a large number of the primary visual cortex neurons operate in a regime called surround modulation. Surround modulation has a substantial effect on various perceptual tasks, and it also plays a crucial role in the efficient neural coding of the visual cortex. Inspired by the notion of surround modulation, we designed new excitatory-inhibitory connections between a unit and its surrounding units in the convolutional neural network (CNN) to achieve a more biologically plausible network. Our experiments show that this simple mechanism can considerably improve both the performance and training speed of traditional CNNs in visual tasks. We further explore additional outcomes of the proposed structure.

Generalization in multitask deep neural classifiers: a statistical physics approach

Neural Information Processing Systems

A proper understanding of the striking generalization abilities of deep neural networks presents an enduring puzzle. Recently, there has been a growing body of numerically-grounded theoretical work that has contributed important insights to the theory of learning in deep neural nets. There has also been a recent interest in extending these analyses to understanding how multitask learning can further improve the generalization capacity of deep neural nets. These studies deal almost exclusively with regression tasks which are amenable to existing analytical techniques. We develop an analytic theory of the nonlinear dynamics of generalization of deep neural networks trained to solve classification tasks using softmax outputs and cross-entropy loss, addressing both single task and multitask settings.

Generative Models for Graph-Based Protein Design

Neural Information Processing Systems

Engineered proteins offer the potential to solve many problems in biomedicine, energy, and materials science, but creating designs that succeed is difficult in practice. A significant aspect of this challenge is the complex coupling between protein sequence and 3D structure, with the task of finding a viable design often referred to as the inverse protein folding problem. We develop relational language models for protein sequences that directly condition on a graph specification of the target structure. Our approach efficiently captures the complex dependencies in proteins by focusing on those that are long-range in sequence but local in 3D space. Our framework significantly improves in both speed and robustness over conventional and deep-learning-based methods for structure-based protein sequence design, and takes a step toward rapid and targeted biomolecular design with the aid of deep generative models.

Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

Neural Information Processing Systems

Learning generative models that span multiple data modalities, such as vision and language, is often motivated by the desire to learn more useful, generalisable representations that faithfully capture common underlying factors between the modalities. In this work, we characterise successful learning of such models as the fulfilment of four criteria: i) implicit latent decomposition into shared and private subspaces, ii) coherent joint generation over all modalities, iii) coherent cross-generation across individual modalities, and iv) improved model learning for individual modalities through multi-modal integration. Here, we propose a mixture-of-experts multi-modal variational autoencoder (MMVAE) for learning of generative models on different sets of modalities, including a challenging image - language dataset, and demonstrate its ability to satisfy all four criteria, both qualitatively and quantitatively. Papers published at the Neural Information Processing Systems Conference.

Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics

Neural Information Processing Systems

Recurrent neural networks (RNNs) are a widely used tool for modeling sequential data, yet they are often treated as inscrutable black boxes. Given a trained recurrent network, we would like to reverse engineer it--to obtain a quantitative, interpretable description of how it solves a particular task. Even for simple tasks, a detailed understanding of how recurrent networks work, or a prescription for how to develop such an understanding, remains elusive. In this work, we use tools from dynamical systems analysis to reverse engineer recurrent networks trained to perform sentiment classification, a foundational natural language processing task. Given a trained network, we find fixed points of the recurrent dynamics and linearize the nonlinear system around these fixed points.

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Neural Information Processing Systems

Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm. We propose a new graph convolutional neural network model for learning branch-and-bound variable selection policies, which leverages the natural variable-constraint bipartite graph representation of mixed-integer linear programs. We train our model via imitation learning from the strong branching expert rule, and demonstrate on a series of hard problems that our approach produces policies that improve upon state-of-the-art machine-learning methods for branching and generalize to instances significantly larger than seen during training. Moreover, we improve for the first time over expert-designed branching rules implemented in a state-of-the-art solver on large problems. Papers published at the Neural Information Processing Systems Conference.

Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks

Neural Information Processing Systems

We propose a novel memory cell for recurrent neural networks that dynamically maintains information across long windows of time using relatively few resources. The Legendre Memory Unit (LMU) is mathematically derived to orthogonalize its continuous-time history -- doing so by solving $d$ coupled ordinary differential equations (ODEs), whose phase space linearly maps onto sliding windows of time via the Legendre polynomials up to degree $d - 1$. Backpropagation across LMUs outperforms equivalently-sized LSTMs on a chaotic time-series prediction task, improves memory capacity by two orders of magnitude, and significantly reduces training and inference times. LMUs can efficiently handle temporal dependencies spanning $100\text{,}000$ time-steps, converge rapidly, and use few internal state-variables to learn complex functions spanning long windows of time -- exceeding state-of-the-art performance among RNNs on permuted sequential MNIST. These results are due to the network's disposition to learn scale-invariant features independently of step size.