Nature

Backpropagation-free spiking neural networks with the forward–forward algorithm

Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm that emulates neuronal activity through discrete spike-based processing. Despite their advantages, training SNNs ...
EurekAlert!

Not so simple machines: Cracking the code for materials that can learn

Obtaining the gradient of what's known as the loss function is an essential step to establish the backpropagation algorithm developed by University of Michigan researchers to train a material. The ...
Nature

Loss of plasticity in deep continual learning

Artificial neural networks, deep-learning methods and the backpropagation algorithm 1 form the foundation of modern machine learning and artificial intelligence. These methods are almost always used ...
EurekAlert!

A backpropagation algorithm for mechanical neural networks (IMAGE)

Obtaining the gradient of what's known as the loss function is an essential step to establish the backpropagation algorithm developed by University of Michigan researchers to train a material. The ...
Semiconductor Engineering

In Situ Backpropagation Strategy That Progressively Updates Neural Network Layers Directly ...

A new technical paper titled “Hardware implementation of backpropagation using progressive gradient descent for in situ training of multilayer neural networks” was published by researchers at ...
The Economist

AI scientists are producing new theories of how the brain learns

Five DECADES of research into artificial neural networks have earned Geoffrey Hinton the moniker of the Godfather of artificial intelligence (AI). Work by his group at the University of Toronto laid ...