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
A review and evaluation of the state-of-the-art in PV solar power forecasting:Techniques and optimization
TL;DR: In this paper, the authors reviewed and evaluated contemporary forecasting techniques for photovoltaics into power grids, and concluded that ensembles of artificial neural networks are best for forecasting short-term PV power forecast and online sequential extreme learning machine superb for adaptive networks; while Bootstrap technique optimum for estimating uncertainty.
Journal ArticleDOI
Computer-aided classification of lung nodules on computed tomography images via deep learning technique.
TL;DR: This study attempted to simplify the image analysis pipeline of conventional CAD with deep learning techniques and introduced models of a deep belief network and a convolutional neural network in the context of nodule classification in computed tomography images.
Journal ArticleDOI
Deep learning for neuroimaging: A validation study
Sergey M. Plis,R Devon Hjelm,Ruslan Salakhutdinov,Elena A. Allen,Elena A. Allen,HJ Bockholt,Jeffrey D. Long,Jeffrey D. Long,Hans J. Johnson,Hans J. Johnson,Jane S. Paulsen,Jane S. Paulsen,Jessica A. Turner,Vince D. Calhoun,Vince D. Calhoun +14 more
TL;DR: In this article, a constraint-based approach to visualizing high dimensional data was proposed to analyze the effect of parameter choices on data transformations and showed that deep learning methods are able to learn physiologically important representations and detect latent relations in neuroimaging data.
Proceedings ArticleDOI
DeepX: a software accelerator for low-power deep learning inference on mobile devices
Nicholas D. Lane,Sourav Bhattacharya,Petko Georgiev,Claudio Forlivesi,Lei Jiao,Lorena Qendro,Fahim Kawsar +6 more
TL;DR: Experiments show, DeepX can allow even large-scale deep learning models to execute efficently on modern mobile processors and significantly outperform existing solutions, such as cloud-based offloading.
Posted Content
Generalized Denoising Auto-Encoders as Generative Models
TL;DR: A different attack on the problem is proposed, which deals with arbitrary (but noisy enough) corruption, arbitrary reconstruction loss, handling both discrete and continuous-valued variables, and removing the bias due to non-infinitesimal corruption noise.
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.