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
Recognition of geochemical anomalies using a deep autoencoder network
Yihui Xiong,Renguang Zuo +1 more
TL;DR: The autoencoder network can be trained to recognize multivariate geochemical anomalies associated with Fe polymetallic mineralization and is demonstrated in a case study southwestern Fujian district (China).
Journal ArticleDOI
A Cost-Sensitive Deep Belief Network for Imbalanced Classification
TL;DR: An evolutionary cost-sensitive deep belief network (ECS-DBN) for imbalanced classification that uses adaptive differential evolution to optimize the misclassification costs based on the training data that presents an effective approach to incorporating the evaluation measure into the objective function.
Proceedings ArticleDOI
Real-Time Brazilian License Plate Detection and Recognition Using Deep Convolutional Neural Networks
TL;DR: This work proposed an end-to-end DL-ALPR system for Brazilian license plates based on state-of-the-art Convolutional Neural Network architectures and was able to correctly detect and recognize all seven characters of a license plate in 63.18% of the test set.
Journal ArticleDOI
Deep learning for determining a near-optimal topological design without any iteration
TL;DR: In this article, a deep learning-based method was proposed to predict an optimized structure for a given boundary condition and optimization setting without using any iterative scheme, which can determine a nearoptimal structure in terms of pixel values and compliance with negligible computational time.
Proceedings ArticleDOI
An Intrusion Detection Model Based on Deep Belief Networks
TL;DR: This paper focuses on an important research problem of Big Data classification in intrusion detection system, and an intrusion detection model based on Deep Belief Networks is proposed to apply in intrusion recognition domain.
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.