scispace - formally typeset
Search or ask a question
Author

Jeffrey Dean

Other affiliations: University of Washington, World Health Organization, Microsoft  ...read more
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.


Papers
More filters
Patent
Simon Tong1, Jeffrey Dean1
30 Apr 2003
TL;DR: In this article, a system automatically creates a list from items in existing lists and assigns weights to the items in the existing lists based on the one or more example items corresponding to the list.
Abstract: A system automatically creates a list from items in existing lists. The system receives one or more example items corresponding to the list and assigns weights to the items in the existing lists based on the one or more example items. The system then forms the list based on the items and the weights assigned to the items.

47 citations

Patent
26 Nov 1997
TL;DR: In this article, a method for guiding virtual-to-physical mapping policies in a computer system including a processor and a memory is provided, where state information is randomly sampled from selected memory references in a stream of memory references issued by the processor to the memory.
Abstract: A method is provided for guiding virtual-to-physical mapping policies in a computer system including a processor and a memory. State information is randomly sampled from selected memory references in a stream of memory references issued by the processor to the memory. Cache hit/miss status, translation-look-aside buffer hit/miss status, and effective virtual and physical memory addresses of the sampled memory references are recorded in a profile record. The recorded information is aggregated by virtual memory address, and a new virtual-to-physical mapping is choosen to reduce cache and translation-look-aside buffer miss rates.

46 citations

Patent
25 Nov 1998
TL;DR: In this paper, an apparatus for sampling states of a computer system having a hierarchical memory arranged at a plurality of levels, the hierarchical memory storing data at addresses, is presented, which includes a selector for selecting memory transactions based on first state and transaction information.
Abstract: An apparatus for sampling states of a computer system having a hierarchical memory arranged at a plurality of levels, the hierarchical memory storing data at addresses. The apparatus includes a selector for selecting memory transactions based on first state and transaction information. The memory transactions are to be processed by the hierarchical memory. A trigger activates the selector based on second state and transaction information. A sampler stores states of the computer system that are identified with the selected instructions while processing the selected memory transactions in the hierarchical memory.

45 citations

Patent
25 Nov 1998
TL;DR: In this paper, a method for analyzing memory transactions processed by memories of a computer system is proposed, where state information from a plurality of consecutive predetermined memory transactions to the selected addresses are recorded while the selected transactions are processed by the memories.
Abstract: A method analyses memory transaction processed by memories of a computer system. The method selects a set of addresses of the memories. State information from a plurality of consecutive predetermined memory transactions to the selected addresses are recorded while the selected transactions are processed by the memories. The selecting and the recording steps are repeated until a termination condition is reached. Then, the recorded state information is statistically analysed to estimate statistics of properties of the memory interactions among contexts in the computer system.

42 citations

Patent
30 Jun 2011
TL;DR: In this article, a system may determine a measure of how a content of a document changes over time, generate a score for the document based, at least in part, on the measure of the content of the document, and rank the document with regard to at least one other document based on the score.
Abstract: A system may determine a measure of how a content of a document changes over time, generate a score for the document based, at least in part, on the measure of how the content of the document changes over time, and rank the document with regard to at least one other document based, at least in part, on the score.

39 citations


Cited by
More filters
Proceedings Article
04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small 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.
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.

55,235 citations

Proceedings Article
01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
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.

49,914 citations

Proceedings ArticleDOI
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
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.

40,257 citations

Book
18 Nov 2016
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
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.

38,208 citations

Proceedings Article
Sergey Ioffe1, Christian Szegedy1
06 Jul 2015
TL;DR: 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.
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.

30,843 citations