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

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 present a new technique called “t-SNE” that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map. t-SNE is better than existing techniques at creating a single map that reveals structure at many different scales. This is particularly important for high-dimensional data that lie on several different, but related, low-dimensional manifolds, such as images of objects from multiple classes seen from multiple viewpoints. For visualizing the structure of very large datasets, we show how t-SNE can use random walks on neighborhood graphs to allow the implicit structure of all of the data to influence the way in which a subset of the data is displayed. We illustrate the performance of t-SNE on a wide variety of datasets and compare it with many other non-parametric visualization techniques, including Sammon mapping, Isomap, and Locally Linear Embedding. The visualizations produced by t-SNE are significantly better than those produced by the other techniques on almost all of the datasets.

/pdf/visualizing-data-using-t-sne-2w1n304iq0.pdf

Visualizing Data using t-SNE

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

We study Markov models whose state spaces arise from the Cartesian product of two or more discrete random variables. We show how to parameterize the transition matrices of these models as a convex combination—or mixture—of simpler dynamical models. The parameters in these models admit a simple probabilistic interpretation and can be fitted iteratively by an Expectation-Maximization (EM) procedure. We derive a set of generalized Baum-Welch updates for factorial hidden Markov models that make use of this parameterization. We also describe a simple iterative procedure for approximately computing the statistics of the hidden states. Throughout, we give examples where mixed memory models provide a useful representation of complex stochastic processes.

/pdf/mixed-memory-markov-models-decomposing-complex-stochastic-8omlc1clcb.pdf

Mixed Memory Markov Models: Decomposing Complex Stochastic Processes as Mixtures of Simpler Ones

We investigate a generalized linear model for dimensionality reduction of binary data. The model is related to principal component analysis (PCA) in the same way that logistic regression is related to linear regression. Thus we refer to the model as logistic PCA. In this paper, we derive an alternating least squares method to estimate the basis vectors and generalized linear coefficients of the logistic PCA model. The resulting updates have a simple closed form and are guaranteed at each iteration to improve the model’s likelihood. We evaluate the performance of logistic PCA—as measured by reconstruction error rates—on data sets drawn from four real world applications. In general, we find that logistic PCA is much better suited to modeling binary data than conventional PCA.

/pdf/a-generalized-linear-model-for-principal-component-analysis-3rcpmrf1kh.pdf

A Generalized Linear Model for Principal Component Analysis of Binary Data

We derive multiplicative updates for solving the nonnegative quadratic programming problem in support vector machines (SVMs). The updates have a simple closed form, and we prove that they converge monotonically to the solution of the maximum margin hyperplane. The updates optimize the traditionally proposed objective function for SVMs. They do not involve any heuristics such as choosing a learning rate or deciding which variables to update at each iteration. They can be used to adjust all the quadratic programming variables in parallel with a guarantee of improvement at each iteration. We analyze the asymptotic convergence of the updates and show that the coefficients of non-support vectors decay geometrically to zero at a rate that depends on their margins. In practice, the updates converge very rapidly to good classifiers.

/pdf/multiplicative-updates-for-nonnegative-quadratic-programming-4phz7fpmzo.pdf

Multiplicative Updates for Nonnegative Quadratic Programming in Support Vector Machines

We develop a framework for large margin classification by Gaussian mixture models (GMMs). Large margin GMMs have many parallels to support vector machines (SVMs) but use ellipsoids to model classes instead of half-spaces. Model parameters are trained discriminatively to maximize the margin of correct classification, as measured in terms of Mahalanobis distances. The required optimization is convex over the model's parameter space of positive semidefinite matrices and can be performed efficiently. Large margin GMMs are naturally suited to large problems in multiway classification; we apply them to phonetic classification and recognition on the TIMIT database. On both tasks, we obtain significant improvement over baseline systems trained by maximum likelihood estimation. For the problem of phonetic classification, our results are competitive with other state-of-the-art classifiers, such as hidden conditional random fields.

Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition

In this paper, we propose a model for representing and predicting distances in large-scale networks by matrix factorization. The model is useful for network distance sensitive applications, such as content distribution networks, topology-aware overlays, and server selections. Our approach overcomes several limitations of previous coordinates-based mechanisms, which cannot model sub-optimal routing or asymmetric routing policies. We describe two algorithms --- singular value decomposition (SVD) and nonnegative matrix factorization (NMF)---for representing a matrix of network distances as the product of two smaller matrices. With such a representation, we build a scalable system--- Internet Distance Estimation Service (IDES)---that predicts large numbers of network distances from limited numbers of measurements. Extensive simulations on real-world data sets show that IDES leads to more accurate, efficient and robust predictions of latencies in large-scale networks than previous approaches.

/pdf/modeling-distances-in-large-scale-networks-by-matrix-4lcau23wkh.pdf

Lawrence K. Saul

Papers

Mixed Memory Markov Models: Decomposing Complex Stochastic Processes as Mixtures of Simpler Ones

A Generalized Linear Model for Principal Component Analysis of Binary Data

Multiplicative Updates for Nonnegative Quadratic Programming in Support Vector Machines

Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition

Modeling distances in large-scale networks by matrix factorization