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.

Automatic identification of related entities

Abstract: In one aspect, the present disclosure can be embodied in a method that includes identifying a collection of entities from one or more data sources, calculating a score for subsets of entities from the collection based on one or more seed entities associated with the collection, identifying one or more entities from each of the subsets based on the calculated score, assigning the calculated score to the identified one or more entities from the respective subset, and ranking the one or more entities based on the assigned score, so as to identify entities in the collection that are related to the one or more seed entities

Query Processing System and Method for Use with Tokenspace Repository

Abstract: A search engine server system receives from a client system a search query and identifies a set of documents in accordance with the search query. A content snippet corresponding to content in a respective document of the identified set of documents is generated, the content snippet associated with at least one query term of the one or more query terms in the search query. A response to the search query is returned to the client system, the response including information identifying at least the respective document and including the content snippet. Generating the content snippet includes performing a first decompression operation on first token identifiers, from a compressed document repository, to provide a set of second token identifiers, and performing a second decompression operation on the set of second token identifiers to recover uncompressed content comprising a portion of the respective document.

System and method for encoding and decoding variable-length data

Abstract: A system and method for encoding and decoding variable-length data includes storing data values in a data structure including a data field and a tag field. The data field includes one or more variable-length data subfields capable of storing variable-length data (e.g., 1 to N bytes of data). In some embodiments, the data subfields and the tag field of the data structure each start on a byte boundary which simplifies decoding. The tag field includes one or more tag subfields, each corresponding to the one or more data subfields. Each tag subfield includes one or more tag bits which indicate the length of the data stored in the corresponding data subfield. Unpacking or decompressing data values from the data structure can be achieved by using a look-up table of offsets and masks, thus reducing the number of bit operations needed to unpack data values from the data structure.

Document treadmilling system and method for updating documents in a document repository and recovering storage space from invalidated documents

Abstract: A tokenspace repository stores documents as a sequence of tokens. The tokenspace repository, as well as the inverted index for the tokenspace repository, uses a data structure that has a first end and a second end and allows for insertions at the second end and deletions from the front end. A document in the tokenspace repository is updated by inserting the updated version into the repository at the second end and invalidating the earlier version. Invalidated documents are not deleted immediately; they are identified in a garbage collection list for later garbage collection. The tokenspace repository is treadmilled to shift invalidated documents to the front end, at which point they may be deleted and their storage space recovered.

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.