Self-supervised learningSelf-supervised learning (SSL) is a paradigm in machine learning for processing data of lower quality, rather than improving ultimate outcomes. Self-supervised learning more closely imitates the way humans learn to classify objects. The typical SSL method is based on an artificial neural network or other model such as a decision list. The model learns in two steps. First, the task is solved based on an auxiliary or pretext classification task using pseudo-labels which help to initialize the model parameters.
BurstingBursting, or burst firing, is an extremely diverse general phenomenon of the activation patterns of neurons in the central nervous system and spinal cord where periods of rapid action potential spiking are followed by quiescent periods much longer than typical inter-spike intervals. Bursting is thought to be important in the operation of robust central pattern generators, the transmission of neural codes, and some neuropathologies such as epilepsy.
KerasKeras is an open-source library that provides a Python interface for artificial neural networks. Keras acts as an interface for the TensorFlow library. Up until version 2.3, Keras supported multiple backends, including TensorFlow, Microsoft Cognitive Toolkit, Theano, and PlaidML. As of version 2.4, only TensorFlow is supported. However, starting with version 3.0 (including its preview version, Keras Core), Keras will become multi-backend again, supporting TensorFlow, JAX, and PyTorch.
All-or-none lawIn physiology, the all-or-none law (sometimes the all-or-none principle or all-or-nothing law) is the principle that if a single nerve fibre is stimulated, it will always give a maximal response and produce an electrical impulse of a single amplitude. If the intensity or duration of the stimulus is increased, the height of the impulse will remain the same. The nerve fibre either gives a maximal response or none at all. It was first established by the American physiologist Henry Pickering Bowditch in 1871 for the contraction of heart muscle.
Phase precessionPhase precession is a neurophysiological process in which the time of firing of action potentials by individual neurons occurs progressively earlier in relation to the phase of the local field potential oscillation with each successive cycle. In place cells, a type of neuron found in the hippocampal region of the brain, phase precession is believed to play a major role in the neural coding of information.
