In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

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

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82% top-5 test error, exceeding the accuracy of human raters.

/pdf/batch-normalization-accelerating-deep-network-training-by-3dkqye6twt.pdf

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Recent work in unsupervised feature learning and deep learning has shown that being able to train large models can dramatically improve performance. In this paper, we consider the problem of training a deep network with billions of parameters using tens of thousands of CPU cores. We have developed a software framework called DistBelief that can utilize computing clusters with thousands of machines to train large models. Within this framework, we have developed two algorithms for large-scale distributed training: (i) Downpour SGD, an asynchronous stochastic gradient descent procedure supporting a large number of model replicas, and (ii) Sandblaster, a framework that supports a variety of distributed batch optimization procedures, including a distributed implementation of L-BFGS. Downpour SGD and Sandblaster L-BFGS both increase the scale and speed of deep network training. We have successfully used our system to train a deep network 30x larger than previously reported in the literature, and achieves state-of-the-art performance on ImageNet, a visual object recognition task with 16 million images and 21k categories. We show that these same techniques dramatically accelerate the training of a more modestly- sized deep network for a commercial speech recognition service. Although we focus on and report performance of these methods as applied to training large neural networks, the underlying algorithms are applicable to any gradient-based machine learning algorithm.

/pdf/large-scale-distributed-deep-networks-22q3vnn2cn.pdf

Large Scale Distributed Deep Networks

Recent advances in deep learning have made the use of large, deep neural networks with tens of millions of parameters suitable for a number of applications that require real-time processing. The sheer size of these networks can represent a challenging computational burden, even for modern CPUs. For this reason, GPUs are routinely used instead to train and run such networks. This paper is a tutorial for students and researchers on some of the techniques that can be used to reduce this computational cost considerably on modern x86 CPUs. We emphasize data layout, batching of the computation, the use of SSE2 instructions, and particularly leverage SSSE3 and SSE4 fixed-point instructions which provide a 3× improvement over an optimized floating-point baseline. We use speech recognition as an example task, and show that a real-time hybrid hidden Markov model / neural network (HMM/NN) large vocabulary system can be built with a 10× speedup over an unoptimized baseline and a 4× speedup over an aggressively optimized floating-point baseline at no cost in accuracy. The techniques described extend readily to neural network training and provide an effective alternative to the use of specialized hardware.

/pdf/improving-the-speed-of-neural-networks-on-cpus-4awxzars3t.pdf

Improving the speed of neural networks on CPUs

Deep neural networks have recently become the gold standard for acoustic modeling in speech recognition systems The key computational unit of a deep network is a linear projection followed by a point-wise non-linearity, which is typically a logistic function In this work, we show that we can improve generalization and make training of deep networks faster and simpler by substituting the logistic units with rectified linear units These units are linear when their input is positive and zero otherwise In a supervised setting, we can successfully train very deep nets from random initialization on a large vocabulary speech recognition task achieving lower word error rates than using a logistic network with the same topology Similarly in an unsupervised setting, we show how we can learn sparse features that can be useful for discriminative tasks All our experiments are executed in a distributed environment using several hundred machines and several hundred hours of speech data

/pdf/on-rectified-linear-units-for-speech-processing-4k31psmgn5.pdf

On rectified linear units for speech processing

We recently showed that Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform state-of-the-art deep neural networks (DNNs) for large scale acoustic modeling where the models were trained with the cross-entropy (CE) criterion. It has also been shown that sequence discriminative training of DNNs initially trained with the CE criterion gives significant improvements. In this paper, we investigate sequence discriminative training of LSTM RNNs in a large scale acoustic modeling task. We train the models in a distributed manner using asynchronous stochastic gradient descent optimization technique. We compare two sequence discriminative criteria – maximum mutual information and state-level minimum Bayes risk, and we investigate a number of variations of the basic training strategy to better understand issues raised by both the sequential model, and the objective function. We obtain significant gains over the CE trained LSTM RNN model using sequence discriminative training techniques.

Sequence Discriminative Distributed Training of Long Short-Term Memory Recurrent Neural Networks

Necessary conditions for asymptotically optimal sliding-block or stationary codes for source coding and rate-constrained simulation of memoryless sources are presented and used to motivate a design technique for trellis-encoded source coding and rate-constrained simulation. The code structure has intuitive similarities to classic random coding arguments as well as to “fake process” methods and alphabet-constrained methods. Experimental evidence shows that the approach provides comparable or superior performance in comparison with previously published methods on common examples, sometimes by significant margins.

Mark Z. Mao

Papers

Large Scale Distributed Deep Networks

Improving the speed of neural networks on CPUs

On rectified linear units for speech processing

Sequence Discriminative Distributed Training of Long Short-Term Memory Recurrent Neural Networks

Rate-Constrained Simulation and Source Coding i.i.d. Sources