I’ve trained this open-source neural network framework on a variety of datasets, including recipes, Pokemon, knock-knock jokes, pick up lines, and D&D spells. Now I give you: training a neural network on the complete list of Dr. Who episodes. (Big shout-out of thanks to blog readers Anya and Dan, who provided the dataset

Batch Normalization standardizes deep network activations using batch statistics to stabilize training, enable higher learning rates, and boost generalization.

The Architecture of Modular Neural Pipelines Optimizing modular neural network pipelines requires a rigorous approach to how individual components

These functions generate parameters that are useful for neural network models

In this chapter, theory, circuit design methodologies and possible applications of Cellular Nanoscale Networks (CNNs) exploiting memristor technology are reviewed. Memristor-based CNNs platforms (MCNNs) make use of memristors to realize analog multiplication circuits

Rizan Bhandari is researcher and full-stack developer based in Kathmandu. He specializes in building modern web platforms and infrastructure.

Abstract page for arXiv paper 1802.08435: Efficient Neural Audio Synthesis

Jan Novak

A technique for training very deep neural networks

Neural networks, architectures and training at depth