Neural networks in the brain are dominated by sometimes more than 60% feedback
connections, which most often have small synaptic weights. Different from this, little is known …

Much of recent machine learning has focused on deep learning, in which neural network
weights are trained through variants of stochastic gradient descent. An alternative approach …

Ongoing studies have identified similarities between neural representations in biological
networks and in deep artificial neural networks. This has led to renewed interest in …

Equilibrium Propagation is a biologically-inspired algorithm that trains convergent recurrent
neural networks with a local learning rule. This approach constitutes a major lead to allow …

Much recent work has focused on biologically plausible variants of supervised learning
algorithms. However, there is no teacher in the motor cortex that instructs the motor neurons …

Artificial neural networks are most commonly trained with the back-propagation algorithm,
where the gradient for learning is provided by back-propagating the error, layer by layer …

During learning, the brain modifies synapses to improve behaviour. In the cortex, synapses
are embedded within multilayered networks, making it difficult to determine the effect of an …

Recent work in computer science has shown the power of deep learning driven by the
backpropagation algorithm in networks of artificial neurons. But real neurons in the brain are …

Researchers have proposed that deep learning, which is providing important progress in a
wide range of high complexity tasks, might inspire new insights into learning in the brain …

The conventional wisdom is that backprop nets with excess hidden units generalize poorly.
We show that nets with excess capacity generalize well when trained with backprop and …