Bayesian neural networks (BNNs) are a principled approach to modeling predictive uncertainties in deep learning, which are important in safety-critical applications. Since exact Bayesian inference over the weights in a BNN is intractable, various approximate inference methods exist, among which sampling methods such as Hamiltonian Monte Carlo (HMC) are often considered the gold standard. While HMC provides high-quality samples, it lacks interpretable summary statistics because its sample mean and variance i

Making a deep convolutional neural network smaller and faster

A generative adversarial network (GAN) is a machine learning model designed to generate realistic data by learning patterns from existing training datasets. It operates within an unsupervised learning framework by using deep learning techniques, where two neural networks work in opposition—one generates data, while the other evaluates whether the data is real or generated

A brief survey about compression techniques based on pruning

Abstract page for arXiv paper 2306.04073: Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks

ReLU, short for Rectified Linear Unit, is an activation function that outputs the input if it is positive and zero otherwise. Its formula is f(x) = max(0, x).

Today we're joined by Alona Fyshe, an assistant professor at the University of Alberta. We caught up with Alona on the heels of an interesting panel discussion that she...

Although the temporal spike dynamics of spiking neural networks (SNNs) enable low-power temporal capture capabilities, they also incur inherent inconsistencies that

Categories Blog Case Studies Documents eBooks News and Events Reference Architecture Supported Software Whitepapers Return to Homepage Artificial Intelligence 5 Types of LSTM Recurrent Neural Networks December 28, 2023 14 min read Before LSTMs - Recurrent Neural Networks Utilizing past experiences to enhance future performance is a key aspect of deep learning, as well as machine learning in general. In neural networks, performance improvement through experience is encoded by model parameters called weights

Skip to content SudoAll About LSTM Networks Explained Posted on March 18, 2025March 3, 2026 by David Saliba Introduction: The Power of LSTMs The Long Short-Term Memory (LSTM) network is a specialised kind of Recurrent Neural Network (RNN) architecture, designed specifically to solve the problem of vanishing gradients that plagues traditional RNNs when dealing with long sequences of data. While standard RNNs struggle to retain information from many steps ago, LSTMs are engineered with a dedicated Cell State