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

An apparatus is provided for collecting state information associated with an execution path of recently processed instructions in a processor pipeline of a computer system. The apparatus identifies a class of instructions to be sampled. Path-identifying state information of a currently processed instruction is sampled when the currently processed instruction belongs to the identified class of instructions. A shift register stores a predetermined number of entries storing selected state information, the shift register is simultaneously sampled along with additional state information about the instruction being executed at the time of sampling.

Apparatus for sampling path history in a processor pipeline

A system for predicting and summarizing medical events from electronic health records includes a computer memory storing aggregated electronic health records from a multitude of patients of diverse age, health conditions, and demographics including medications, laboratory values, diagnoses, vital signs, and medical notes. The aggregated electronic health records are converted into a single standardized data structure format and ordered arrangement per patient, e.g., into a chronological order. A computer (or computer system) executes one or more deep learning models trained on the aggregated health records to predict one or more future clinical events and summarize pertinent past medical events related to the predicted events on an input electronic health record of a patient having the standardized data structure format and ordered into a chronological order. An electronic device configured with a healthcare provider-facing interface displays the predicted one or more future clinical events and the pertinent past medical events of the patient.

System and Method for Predicting and Summarizing Medical Events from Electronic Health Records

Methods and apparatus determine equivalent descriptions for an information need. In one implementation, if adjacent entries in a query log contain common terms, the uncommon terms are identified as a candidate pair. The candidate pairs are assigned a score based on their frequency of occurrence, and pairs having a score exceeding a defined threshold are determined to be synonyms.

Methods and apparatus for determining equivalent descriptions for an information need

For the past five years, the Google Brain team has focused on conducting research in difficult problems in artificial intelligence, on building large-scale computer systems for machine learning research, and, in collaboration with many teams at Google, on applying our research and systems to dozens of Google products. Our group has recently open-sourced the TensorFlow system (tensorflow.org), a system designed to easily express machine ideas, and to quickly train, evaluate and deploy machine learning systems. In this talk, I'll highlight some of the design decisions we made in building TensorFlow, discuss research results produced within our group, and describe ways in which these ideas have been applied to a variety of problems in Google's products, usually in close collaboration with other teams. This talk describes joint work with many people at Google.

Large-Scale Deep Learning For Building Intelligent Computer Systems

of EP0919919A method for sampling the performance of a computer system is provided. The computer system includes a plurality of functional units. The method selects transactions to be processed by a particular functional unit of the computer system. State information is stored while the selected transactions are processed by the functional unit. The state information is analyzed to guide optimization.

Jeffrey Dean

Papers

Apparatus for sampling path history in a processor pipeline

System and Method for Predicting and Summarizing Medical Events from Electronic Health Records

Methods and apparatus for determining equivalent descriptions for an information need

Large-Scale Deep Learning For Building Intelligent Computer Systems

System and method for optimising the performance of a computer system