Jeffrey Dean

Bio: Jeffrey Dean is an academic researcher from Google. The author has contributed to research in topics: Deep learning & Web search query. The author has an hindex of 83, co-authored 242 publications receiving 179031 citations. Previous affiliations of Jeffrey Dean include University of Washington & World Health Organization.

Selective specialization for object-oriented languages

Abstract: Dynamic dispatching is a major source of run-time overhead in object-oriented languages, due both to the direct cost of method lookup and to the indirect effect of preventing other optimizations. To reduce this overhead, optimizing compilers for object-oriented languages analyze the classes of objects stored in program variables, with the goal of bounding the possible classes of message receivers enough so that the compiler can uniquely determine the target of a message send at compile time and replace the message send with a direct procedure call. Specialization is one important technique for improving the precision of this static class information: by compiling multiple versions of a method, each applicable to a subset of the possible argument classes of the method, more precise static information about the classes of the method's arguments is obtained. Previous specialization strategies have not been selective about where this technique is applied, and therefore tended to significantly increase compile time and code space usage, particularly for large applications. In this paper, we present a more general framework for specialization in object-oriented languages and describe a goal directed specialization algorithm that makes selective decisions to apply specialization to those cases where it provides the highest benefit. Our results show that our algorithm improves the performance of a group of sizeable programs by 65% to 275% while increasing compiled code space requirements by only 4% to 10%. Moreover, when compared to the previous state-of-the-art specialization scheme, our algorithm improves performance by 11% to 67% while simultaneously reducing code space requirements by 65% to 73%.

System and method for analyzing data records

Abstract: A method and system for analyzing data records includes allocating groups of records to respective processes of a first plurality of processes executing in parallel. In each respective process of the first plurality of processes, for each record in the group of records allocated to the respective process, a query is applied to the record so as to produce zero or more values. Zero or more emit operators are applied to each of the zero or more produced values so as to add corresponding information to an intermediate data structure. Information from a plurality of the intermediate data structures is aggregated to produce output data.

Profile-guided receiver class prediction

Abstract: The use of dynamically-dispatched procedure calls is a key mechanism for writing extensible and flexible code in object-oriented languages. Unfortunately, dynamic dispatching imposes a runtime performance penalty. Some recent implementations of pure object-oriented languages have utilized profile-guided receiver class prediction to reduce this performance penalty, and some researchers have argued for applying receiver class prediction in hybrid languages like C++. We performed a detailed examination of the dynamic profiles of eight large object-oriented applications written in C++ and Cecil, determining that the receiver class distributions are strongly peaked and stable across both inputs and program versions through time. We describe techniques for gathering and manipulating profile information at varying degrees of precision, particularly in the presence of optimizations such as inlining. Our implementation of profile-guided receiver class prediction improves the performance of large Cecil applications by more than a factor of two over solely static optimizations.

Ranking documents based on user behavior and/or feature data

Abstract: A system generates a model based on feature data relating to different features of a link from a linking document to a linked document and user behavior data relating to navigational actions associated with the link. The system also assigns a rank to a document based on the model.

The Beckman Report on Database Research

Abstract: Every few years a group of database researchers meets to discuss the state of database research, its impact on practice, and important new directions. This report summarizes the discussion and conclusions of the eighth such meeting, held October 14- 15, 2013 in Irvine, California. It observes that Big Data has now become a defining challenge of our time, and that the database research community is uniquely positioned to address it, with enormous opportunities to make transformative impact. To do so, the report recommends significantly more attention to five research areas: scalable big/fast data infrastructures; coping with diversity in the data management landscape; end-to-end processing and understanding of data; cloud services; and managing the diverse roles of people in the data life cycle.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: 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

Abstract: 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.

Going deeper with convolutions

Abstract: 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.

Deep Learning

Abstract: 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.

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

Abstract: 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.