Neural Network

What is Constant Error Carrousel? The vanishing gradient problem, a major issue in training recurrent neural networks, is resolved by the Constant Error Carousel (CEC),...

The Neural Turing Machines (NTM) neural network architecture couples standard neural networks with external memory resources to greatly increase their capabilities. It draws on...

A gradient-based learning approach for recurrent neural networks (RNNs) is called Back-Propagation Through Time (BPTT). It works by sending error signals "backwards in time"...

For recurrent neural networks (RNNs), Real-Time Recurrent Learning (RTRL) is a gradient-based learning algorithm. One of the most popular algorithms for teaching RNNs what...

Traditional Recurrent Neural Networks (RNNs) struggle to learn long-term dependencies. The Gated Recurrent Unit (GRU) solves this problem. Recent proposals by Cho et al....

What is LSTM? The powerful Long Short-Term Memory (LSTM) unit overcomes many obstacles in training recurrent neural networks (RNNs), particularly learning long-term dependencies. Details about the...

Denoising Autoencoders (DAEs) are a variant of the fundamental autoencoder architecture that reconstructs a clean input from a corrupted version in order to develop...

Introduction Variational Autoencoders (VAEs) are useful for approximate inference and learning in directed probabilistic models with continuous latent variables with intractable posterior distributions and big...

What is autoencoders ? Neural networks called autoencoders are mostly used for unsupervised learning, particularly for tasks like data denoising, feature learning, and dimensionality reduction. The...

Introduction A potent class of models, convolutional neural networks (CNNs) are said to have a significant influence on computer vision applications. They have produced state-of-the-art...