Publications
Explore 80 academic publications
A Fast Learning Algorithm for Deep Belief Nets
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. U...
Embryonic Stem Cell Lines Derived from Human Blastocysts
Human blastocyst-derived, pluripotent cell lines are described that have normal karyotypes, express high levels of telomerase activity, and express cell surface markers that cha...
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
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. T...
Rectified Linear Units Improve Restricted Boltzmann Machines
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that al...
Generative adversarial networks
Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a c...
A survey on Image Data Augmentation for Deep Learning
Abstract Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfi...
ASPECTS OF THE THEORY OF SYNTAX
Abstract : Contents: Methodological preliminaries: Generative grammars as theories of linguistic competence; theory of performance; organization of a generative grammar; justifi...
High-Resolution Image Synthesis with Latent Diffusion Models
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image da...
Accuracy of clinical diagnosis of idiopathic Parkinson's disease: a clinico-pathological study of 100 cases.
Few detailed clinico-pathological correlations of Parkinson's disease have been published. The pathological findings in 100 patients diagnosed prospectively by a group of consul...