Neural Networks for Action Learning: Three-Factor Rules and Dopamine

This lecture covers the implementation of three-factor rules in the brain for reinforcement learning, focusing on the role of dopamine as the 'Third Factor'. It discusses how neural networks learn by reward, the concept of actor-critic structures in the brain, and the impact of synaptic plasticity on connection strength. The lecture also explores the influence of neuromodulators like dopamine as the Third Factor for synaptic changes, emphasizing the global signal it provides for all synapses. Additionally, it delves into the role of dopamine in broadcasting reward signals and predicting expected rewards, highlighting its significance in the learning process.

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (55)

Related concepts (30)

CS-456: Artificial neural networks/reinforcement learning

Since 2010 approaches in deep learning have revolutionized fields as diverse as computer vision, machine learning, or artificial intelligence. This course gives a systematic introduction into influent

In neuroscience, synaptic plasticity is the ability of synapses to strengthen or weaken over time, in response to increases or decreases in their activity. Since memories are postulated to be represented by vastly interconnected neural circuits in the brain, synaptic plasticity is one of the important neurochemical foundations of learning and memory (see Hebbian theory). Plastic change often results from the alteration of the number of neurotransmitter receptors located on a synapse.

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Neuromodulation is the physiological process by which a given neuron uses one or more chemicals to regulate diverse populations of neurons. Neuromodulators typically bind to metabotropic, G-protein coupled receptors (GPCRs) to initiate a second messenger signaling cascade that induces a broad, long-lasting signal. This modulation can last for hundreds of milliseconds to several minutes. Some of the effects of neuromodulators include: alter intrinsic firing activity, increase or decrease voltage-dependent currents, alter synaptic efficacy, increase bursting activity and reconfiguration of synaptic connectivity.

A neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.

Spike-timing-dependent plasticity (STDP) is a biological process that adjusts the strength of connections between neurons in the brain. The process adjusts the connection strengths based on the relative timing of a particular neuron's output and input action potentials (or spikes). The STDP process partially explains the activity-dependent development of nervous systems, especially with regard to long-term potentiation and long-term depression.

Surprise, Curiosity and Reward: An Evolutionary Perspective

Explores the evolutionary perspective on surprise, curiosity, and reward, focusing on the role of primary and secondary reward signals.

Neural Networks for Action Learning: Brain Implementation Insights CS-456: Artificial neural networks/reinforcement learning

Explores neural networks for action learning and the brain's reinforcement learning implementation.

Neural Networks: Multilayer Learning PHYS-467: Machine learning for physicists

Covers the fundamentals of multilayer neural networks and deep learning, including back-propagation and network architectures like LeNet, AlexNet, and VGG-16.

Neural Networks: Deep Neural Networks MATH-212: Analyse numérique et optimisation

Explores the basics of neural networks, with a focus on deep neural networks and their architecture and training.

AI Gamer: D4 ME-314: Concurrent engineering project

Explores reinforcement learning in AI to master games using neural networks.