We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

/pdf/reinforcement-learning-an-introduction-rzxgej9p17.pdf

Reinforcement Learning: An Introduction

We describe latent Dirichlet allocation (LDA), a generative probabilistic model for collections of discrete data such as text corpora. LDA is a three-level hierarchical Bayesian model, in which each item of a collection is modeled as a finite mixture over an underlying set of topics. Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities. In the context of text modeling, the topic probabilities provide an explicit representation of a document. We present efficient approximate inference techniques based on variational methods and an EM algorithm for empirical Bayes parameter estimation. We report results in document modeling, text classification, and collaborative filtering, comparing to a mixture of unigrams model and the probabilistic LSI model.

/pdf/latent-dirichlet-allocation-4gmscb06en.pdf

Latent dirichlet allocation

We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.

/pdf/latent-dirichlet-allocation-rkwbqihm3p.pdf

Latent Dirichlet Allocation

For the problem of high-dimensional sparse linear regression, it is known that an $\ell_0$-based estimator can achieve a $1/n$ "fast" rate on the prediction error without any conditions on the design matrix, whereas in absence of restrictive conditions on the design matrix, popular polynomial-time methods only guarantee the $1/\sqrt{n}$ "slow" rate. In this paper, we show that the slow rate is intrinsic to a broad class of M-estimators. In particular, for estimators based on minimizing a least-squares cost function together with a (possibly non-convex) coordinate-wise separable regularizer, there is always a "bad" local optimum such that the associated prediction error is lower bounded by a constant multiple of $1/\sqrt{n}$. For convex regularizers, this lower bound applies to all global optima. The theory is applicable to many popular estimators, including convex $\ell_1$-based methods as well as M-estimators based on nonconvex regularizers, including the SCAD penalty or the MCP regularizer. In addition, for a broad class of nonconvex regularizers, we show that the bad local optima are very common, in that a broad class of local minimization algorithms with random initialization will typically converge to a bad solution.

Optimal prediction for sparse linear models? Lower bounds for coordinate-separable M-estimators

Eleventh IEEE International Conference on Computer Vision (ICCV 2007), Rio de Janeiro, Brazil, October 14-20, 2007

The phenomenon of "Big Data" is creating a need for research perspectives that blend computational thinking (with its focus on, e.g., abstractions, algorithms and scalability) with inferential thinking (with its focus on, e.g., underlying populations, sampling patterns, error bars and predictions). Database researchers and statistical machine learning researchers are centrally involved in the creation of this blend, and research that incorporates perspectives from both databases and machine learning will be of particular value in the bigger picture. This is true both for methodology and for theory. I present highlights of several research initiatives that draw jointly on database and statistical foundations, including work on concurrency control and distributed inference, subsampling, time/data tradeoffs and inference/privacy tradeoffs.

/pdf/computational-thinking-inferential-thinking-and-big-data-p0zvfhelmz.pdf

Computational Thinking, Inferential Thinking and "Big Data"

This work presents a 1.5 nJ/classification (nJ/cls) seizure detection classifier which provides unsupervised online updates on an initial offline-trained regression model to achieve >97% average sensitivity and specificity on 27 patient datasets, including three that have >250 hours of continuous recording. The classifier was fabricated in 28nm CMOS and operates at 0.5V supply. Through hardware optimizations and low overall computational complexity and voltage scaling, the online learning classifier achieves 24× better energy per classification and occupies 10x lower area than state-of-the-art.

A 1.5nJ/cls Unsupervised Online Learning Classifier for Seizure Detection

The “sequential neural network” proposed by Jordan (MIT COINS Technical Report 88‐27, 1988) enables learning of motor skill problems involving excess degrees of freedom. This structure was used with (i) the articulatory model developed by Meada [J. Acoust. Soc. Am. Suppl. 1 65, S22 (1979)] as an internal “forward” model relating a given set of articulatory commands (five articulators, e.g., lips, jaws, tongue body, tongue dorsum, and tongue tip) to their acoustic consequences, (ii) vocalic targets specified in the formant (F1, F2, F3) space, and (iii) smoothness constraints leading to coarticulation phenomena. A first set of results about learning of such vocalic gestures will be presented and the following will be discussed: (i) the pattern of coarticulation phenomena observed in this structure, such as between‐articulator relationships for achieving a given formant target and temporal organization of the trajectories in the articulatory space, (ii) the role of gesture duration, and (iii) the compensation ability of the network in relation to perturbations such as those observed in the bite‐block experiments by Lindblom et al. [J. Phonet. 7, 147–162 (1979)].

Michael I. Jordan

Papers

Optimal prediction for sparse linear models? Lower bounds for coordinate-separable M-estimators

Eleventh IEEE International Conference on Computer Vision (ICCV 2007), Rio de Janeiro, Brazil, October 14-20, 2007

Computational Thinking, Inferential Thinking and "Big Data"

A 1.5nJ/cls Unsupervised Online Learning Classifier for Seizure Detection

Simulation of vocalic gestures using an articulatory model driven by a sequential neural network