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

Learning curve bounds for a Markov decision process with undiscounted rewards

In his 2001 monograph Tonal Pitch Space, Fred Lerdahl defined a distance function over tonal and post-tonal harmonies distilled from years of research on music cognition. Although this work references the toroidal structure commonly associated with harmonic space, it stops short of presenting an explicit embedding of this torus. It is possible to use statistical techniques to recreate such an embedding from the distance function, yielding a more complex structure than the standard toroidal model has heretofore assumed. Nonlinear techniques can reduce the dimensionality of this structure and be tuned to emphasize global or local anatomy. The resulting manifolds highlight the relationships inherent in the tonal system and offer a basis for future work in machine-assisted analysis and music theory. Comments Presented at the International Computer Music Conference (ICMC 2005 : free sound), Paper ID 1200, held in Barcelona, September 5-9, 2005. http://www.icmc2005.org/index.php?selectedPage=119 This conference paper is available at ScholarlyCommons: http://repository.upenn.edu/cis_papers/193 VISUALIZATION OF LOW DIMENSIONAL STRUCTURE IN TONAL PITCH SPACE J. Ashley Burgoyne and Lawrence K. Saul Department of Computer and Information Science University of Pennsylvania {burgoyne,lsaul}@cis.upenn.edu

/pdf/visualization-of-low-dimensional-structure-in-tonal-pitch-418senndbf.pdf

Visualization of low dimensional structure in tonal pitch space

We develop a framework to detect when certain sounds are present in a mixed audio signal. We focus on the regime where out of a large number of possible sounds, a small but unknown number are combined and overlapped to yield the observed signal. To infer which sounds are present, we attempt to decompose the observed signal as a linear combination of a small number of sources. To encourage sparse solutions with this property, we balance the modeling errors from individual sources against an l 1 -norm penalty of the type used in basis pursuit and regularized linear regression with grouped variables. Our approach can be viewed as a novel generalization of basis pursuit in two ways: first, with a dictionary of fixed size, we attempt to model acoustic waveforms of potentially variable duration; second, for dictionary entries, we do not store basis vectors representing static templates, but the coefficients of autoregressive models that characterize the acoustic variability of individual sources. We derive the required optimizations in this framework and present experimental results on combinations of periodic and aperiodic sources.

/pdf/sparse-decomposition-of-mixed-audio-signals-by-basis-pursuit-1t9a51xrhu.pdf

Sparse decomposition of mixed audio signals by basis pursuit with autoregressive models

In this paper, we explore an application of basis pursuit to audio scene analysis. The goal of our work is to detect when certain sounds are present in a mixed audio signal. We focus on the regime where out of a large number of possible sources, a small but unknown number combine and overlap to yield the observed signal. To infer which sounds are present, we decompose the observed signal as a linear combination of a small number of active sources. We cast the inference as a regularized form of linear regression whose sparse solutions yield decompositions with few active sources. We characterize the acoustic variability of individual sources by autoregressive models of their time domain waveforms. When we do not have prior knowledge of the individual sources, the coefficients of these autoregressive models must be learned from audio examples. We analyze the dynamical stability of these models and show how to estimate stable models by substituting a simple convex optimization for a difficult eigenvalue problem. We demonstrate our approach by learning dictionaries of musical notes and using these dictionaries to analyze polyphonic recordings of piano, cello, and violin.

/pdf/learning-dictionaries-of-stable-autoregressive-models-for-2bn2c4r4co.pdf

Learning dictionaries of stable autoregressive models for audio scene analysis

When software developers modify one or more files in a large code base, they must also identify and update other related files. Many file dependencies can be detected by mining the development history of the code base: in essence, groups of related files are revealed by the logs of previous workflows. From data of this form, we show how to detect dependent files by solving a problem in binary matrix completion. We explore different latent variable models (LVMs) for this problem, including Bernoulli mixture models, exponential family PCA, restricted Boltzmann machines, and fully Bayesian approaches. We evaluate these models on the development histories of three large, open-source software systems: Mozilla Fire-fox, Eclipse Subversive, and Gimp. In all of these applications, we find that LVMs improve the performance of related file prediction over current leading methods.

/pdf/latent-variable-models-for-predicting-file-dependencies-in-559429gtf2.pdf

Lawrence K. Saul

Papers

Learning curve bounds for a Markov decision process with undiscounted rewards

Visualization of low dimensional structure in tonal pitch space

Sparse decomposition of mixed audio signals by basis pursuit with autoregressive models

Learning dictionaries of stable autoregressive models for audio scene analysis

Latent Variable Models for Predicting File Dependencies in Large-Scale Software Development