NeurotransmetteurLes neurotransmetteurs, ou neuromédiateurs, sont des composés chimiques libérés par les neurones (et parfois par les cellules gliales) agissant sur d'autres neurones, appelés neurones postsynaptiques, ou, plus rarement, sur d'autres types de cellules (comme les cellules musculaires et les cellules gliales comme les astrocytes). Les neurotransmetteurs sont stockés au niveau de l'élément présynaptique dans des vésicules. Le contenu de ces vésicules est libéré (de à molécules en moyenne) dans l'espace synaptique au moment de l'arrivée d'un potentiel d'action.
Interaction informationThe interaction information is a generalization of the mutual information for more than two variables. There are many names for interaction information, including amount of information, information correlation, co-information, and simply mutual information. Interaction information expresses the amount of information (redundancy or synergy) bound up in a set of variables, beyond that which is present in any subset of those variables. Unlike the mutual information, the interaction information can be either positive or negative.
Delta ruleIn machine learning, the delta rule is a gradient descent learning rule for updating the weights of the inputs to artificial neurons in a single-layer neural network. It is a special case of the more general backpropagation algorithm. For a neuron with activation function , the delta rule for neuron 's th weight is given by where It holds that and . The delta rule is commonly stated in simplified form for a neuron with a linear activation function as While the delta rule is similar to the perceptron's update rule, the derivation is different.