In-memory Reservoir Computing: exploiting memristive devices in Spiking Neural Networks
Filippo Moro
In-memory Reservoir Computing: exploiting memristive devices in Spiking Neural Networks.
Rel. Carlo Ricciardi. Politecnico di Torino, Master of science program in Nanotechnologies For Icts, 2019
|
Preview |
PDF (Tesi_di_laurea)
- Thesis
Licence: Creative Commons Attribution Non-commercial No Derivatives. Download (6MB) | Preview |
|
|
Archive (ZIP) (Documenti_allegati)
- Other
Licence: Creative Commons Attribution Non-commercial No Derivatives. Download (4MB) |
Abstract
Neuromorphic computing has often lent on analysis of biological systems to improve its performances. One of the key properties of the Nervous System is Plasticity, i.e. the capacity of its components (Neuron and Synapses) to modify themselves, functionally and structurally, in response to experience and injury. In the brain, plasticity is mainly attributed to Synapses, which control the flow of ions between Neurons through neurotransmitters with a certain, variable in time, weight. Neurons also play a role in plasticity mechanisms, since their excitability can be varied as well as the leakages of internalized ions to keep a healthy firing regime, minimizing energy consumption and maximizing information transfer.
These plasticity mechanisms applied to Neural Networks not only increase the plausibility to biology but also contribute to improving the performances of the system in several tasks
Relators
Publication type
URI
![]() |
Modify record (reserved for operators) |
