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
Book ChapterDOI
Unsupervised Feature Learning for RGB-D Based Object Recognition
TL;DR: HMP uses sparse coding to learn hierarchical feature representations from raw RGB-D data in an unsupervised way and enables superior object recognition results using linear support vector machines.
Journal ArticleDOI
A Review of Human Activity Recognition Methods
TL;DR: This work proposes a categorization of human activity methodologies and divides human activity classification methods into two large categories according to whether they use data from different modalities or not, and examines the requirements for an ideal human activity recognition dataset.
Posted Content
Advances in Optimizing Recurrent Networks
TL;DR: Experiments reported here evaluate the use of clipping gradients, spanning longer time ranges with leaky integration, advanced momentum techniques, using more powerful output probability models, and encouraging sparser gradients to help symmetry breaking and credit assignment.
Book ChapterDOI
Deep learning of representations: looking forward
TL;DR: This paper proposes to examine some of the challenges of scaling deep learning algorithms to much larger models and datasets, reducing optimization difficulties due to ill-conditioning or local minima, designing more efficient and powerful inference and sampling procedures, and learning to disentangle the factors of variation underlying the observed data.
Journal ArticleDOI
Rolling bearing fault diagnosis using an optimization deep belief network
TL;DR: Stochastic gradient descent is used to efficiently fine-tune all the connection weights after the pre-training of restricted Boltzmann machines (RBMs) based on the energy functions, and the classification accuracy of the DBN is improved.
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.