Bio-inspired artificial neural networks
Project is carried out within the TEAM-NET programme of the Foundation for Polish Science
Artificial neural network model was created basing on analogies to biological counterparts, such as a simplified model of the neuron or a system of retinal neurons.
Due to the increasing complexity of tasks and problems with the development of effective methods for learning deep neural networks, solutions based on algebraic structures dominate Today, advanced approaches in machine learning such as deep learning show a number of undesirable features, such as forgetfulness, susceptibility to adversarial examples, the requirement for a large training set, and slow learning.
Most of these features do not occur in biological systems, thus it would be beneficial to take an inspiration from them to help training artificial systems.
The aim of the project is to analyze high-level behaviors of biological neural systems and to build innovative artificial models by proposing new paradigms of learning and new architectures of computational models.
The Jagiellonian University runs six research groups : Cognitive group (leader Tadeusz Marek), Physics-group (leader Maciej A.
Nowak), Machine-learning group, Neuro-group, BioDataScience-group, InfoTech-group.
We seek for a PhD Student of the Physics group.
The responsibility of the potential contractor shall be :
1. analysis of large sets of neuronal data
2. numerical cross-check of the models of correlations
Skills / Qualifications
1. a participant in doctoral studies run by an authorized university organizational unit,
2. knowledge of the methods in the complexity theory
3. good knowledge of English,
4. knowledge of environments and programming tools for ML.