logo SBA

ETD

Digital archive of theses discussed at the University of Pisa

 

Thesis etd-03292019-220853


Thesis type
Tesi di laurea magistrale
Author
LAGANI, GABRIELE
email address
gabriele.lagani@gmail.com
URN
etd-03292019-220853
Thesis title
Hebbian Learning Algorithms for Training Convolutional Neural Networks
Department
INGEGNERIA DELL'INFORMAZIONE
Course of study
COMPUTER ENGINEERING
Supervisors
relatore Amato, Giuseppe
relatore Falchi, Fabrizio
relatore Gennaro, Claudio
Keywords
  • computer
  • convolutional
  • deep
  • Hebbian
  • learning
  • networks
  • neural
  • python
  • pytorch
  • vision
Graduation session start date
03/05/2019
Availability
Full
Summary
The concept of Hebbian learning refers to a family of learning rules, inspired by biology, according to which the weight associated with a synapse increases proportionally to the values of the pre-synaptic and post-synaptic stimuli at a given instant of time. Different variants of Hebbian rules can be found in literature. In this thesis, three main Hebbian learning approaches are explored: Winner-Takes-All competition, Self-Organizing Maps and a supervised Hebbian learning solution for training the final classification layer of a network. In literature, applications of Hebbian learning rules to train networks for image classification tasks exist, although they are currently limited to relatively shallow architectures. In this thesis, the possibility of applying Hebbian learning rules to deeper network architectures is explored and the results are compared to those achieved with Gradient Descent on the same architectures.
File