Journal ArticleDOI
A fast learning algorithm for deep belief nets
Reads0
Chats0
TLDR
A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.Abstract:
We show how to use "complementary priors" to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modeled by long ravines in the free-energy landscape of the top-level associative memory, and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind.read more
Citations
More filters
Journal ArticleDOI
Development of a real-time endoscopic image diagnosis support system using deep learning technology in colonoscopy.
Masayoshi Yamada,Yutaka Saito,Hitoshi Imaoka,Masahiro Saiko,Shigemi Yamada,Hiroko Kondo,Hiroyuki Takamaru,Taku Sakamoto,Jun Sese,Aya Kuchiba,Taro Shibata,Ryuji Hamamoto +11 more
TL;DR: An artificial intelligence (AI) system that automatically detects early signs of colorectal cancer during colonoscopy and can alert endoscopists in real-time to avoid missing abnormalities such as non-polypoid polyps during Colonoscopy, improving the early detection of this disease.
Journal ArticleDOI
Computational mechanics enhanced by deep learning
Atsuya Oishi,Genki Yagawa +1 more
TL;DR: A new method of numericalquadrature for the FEM stiffness matrices is developed by using the proposed method, where a kind of optimized quadrature rule superior in accuracy to the standard Gauss–Legendre quadratures is obtained on the element-by-element basis.
Proceedings ArticleDOI
Convolutional recurrent neural networks: Learning spatial dependencies for image representation
TL;DR: The convolutional recurrent neural network (C-RNN) is proposed, which learns the spatial dependencies between image regions to enhance the discriminative power of image representation and achieves competitive performance on ILSVRC 2012, SUN 397, and MIT indoor.
Book ChapterDOI
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks
TL;DR: This paper presents a framework for training hierarchical feed-forward models for visual recognition, using transfer learning from pseudo tasks, and shows that these pseudo tasks induce an informative inverse-Wishart prior on the functional behavior of the network, offering an effective way to incorporate useful prior knowledge into the network training.
Proceedings ArticleDOI
NeuroStylist: Neural Compatibility Modeling for Clothing Matching
TL;DR: A content-based neural scheme is proposed to model the compatibility between fashion items based on the Bayesian personalized ranking (BPR) framework that is able to jointly model the coherent relation between modalities of items and their implicit matching preference.
References
More filters
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Book
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
TL;DR: Probabilistic Reasoning in Intelligent Systems as mentioned in this paper is a complete and accessible account of the theoretical foundations and computational methods that underlie plausible reasoning under uncertainty, and provides a coherent explication of probability as a language for reasoning with partial belief.
Journal ArticleDOI
Shape matching and object recognition using shape contexts
TL;DR: This paper presents work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation, and proposes shape detection using a feature called shape context, which is descriptive of the shape of the object.
Journal ArticleDOI
Training products of experts by minimizing contrastive divergence
TL;DR: A product of experts (PoE) is an interesting candidate for a perceptual system in which rapid inference is vital and generation is unnecessary because it is hard even to approximate the derivatives of the renormalization term in the combination rule.
Proceedings ArticleDOI
Best practices for convolutional neural networks applied to visual document analysis
TL;DR: A set of concrete bestpractices that document analysis researchers can use to get good results with neural networks, including a simple "do-it-yourself" implementation of convolution with a flexible architecture suitable for many visual document problems.