Continuous Learning and Adaptation with Membrane Potential and Activation Threshold Homeostasis
This work addresses the problem of incorporating biological realism into neural networks for researchers in computational neuroscience and AI, though it appears incremental as it builds on existing biologically inspired models.
The paper tackles the limitation of classical neural networks in modeling internal neuron dynamics by introducing the MPATH neuron model, which simulates biologically inspired mechanisms to maintain dynamic equilibrium and enable temporal processing without recurrent connections, demonstrating adaptation and continuous learning in experiments.
Most classical (non-spiking) neural network models disregard internal neuron dynamics and treat neurons as simple input integrators. However, biological neurons have an internal state governed by complex dynamics that plays a crucial role in learning, adaptation and the overall network activity and behaviour. This paper presents the Membrane Potential and Activation Threshold Homeostasis (MPATH) neuron model, which combines several biologically inspired mechanisms to efficiently simulate internal neuron dynamics with a single parameter analogous to the membrane time constant in biological neurons. The model allows neurons to maintain a form of dynamic equilibrium by automatically regulating their activity when presented with fluctuating input. One consequence of the MPATH model is that it imbues neurons with a sense of time without recurrent connections, paving the way for modelling processes that depend on temporal aspects of neuron activity. Experiments demonstrate the model's ability to adapt to and continually learn from its input.