The Theory of Perfect Learning
| Submitted by : | Nonvikan Karl-Augustt Alahassa |
| University: | University of Montreal |
| E-mail : | alahassan@dms.umontreal.ca |
| Supervisor's Name : | Alejandro Murua |
| Year of award : | |
| Awards : | 2021 |
The perfect learning exists. We mean a learning model that can be generalized and moreover that can always fit perfectly the test data as well as the training data. We have performed in this thesis many experiments that validate this concept in many ways. The tools are given through the chapters that contain our developments. The classical Multilayer Feedforward model has been re-considered and a novel N_k-architecture is proposed to fit any multivariate regression task. This model can easily be augmented to thousands of possible layers without loss of predictive power and has the potential to overcome our difficulties simultaneously in building a model that has a good fit on the ...
1. Statistical topics
2. The Potts Model with Complete Shrinkage
3. Deep learning and Classical Neural Networks
4. Shallow Potts Neural Network Mixture Models
5. Nearest Neighbor Multivariate Interpolation (NNMI)
6. Generalization of similarity measure using Metric Learning
7. Convolutional Neural Network Gibbs Model
8. Concluding Remarks, Discussion notes & Applications
Download PDF