bionics-engineering:computational-neuroscience:cns2016
Applied Brain Science - Computational Neuroscience (CNS)
Lectures and Materials for Academic Year 2015/16
| Date | Room | Topic | References & Additional Material | |
|---|---|---|---|---|
| 1 | 29/2/16 (11.30-13.30) | SI 3 | Introduction to the course | Lecture 1 |
| 2 | 02/3/16 (14.30-17.30) | C44 | Neural Modeling | Lecture 2 |
| 3 | 07/3/16 (11.30-13.30) | SI 3 | Lab1 | Implementing Spiking Neurons using Izhikevich's Model |
| 4 | 09/3/16 (15.30-18.30) | SI 3 | Neuron-Astrocyte models | Lecture 3 |
| 5 | 14/3/16 (11.30-13.30) | SI 3 | Lab2 | Implementing a Spiking Neural Network |
| 6 | 16/3/16 (15.30-18.30) | SI 3 | In-vitro Models | Lecture 4: Statistics for In-vistro neuro-astrocyte culture |
| 7 | 21/3/16 (11.30-13.30) | SI 3 | Lab3 | Implementing a Spiking Neuron-Astrocyte Network |
| 8 | 04/04/16 (11.30-13.30) | SI 3 | Computation of Touch and Vision sensory input | Lecture 5 |
| 9 | 06/04/16 (15.30-18.30) | SI 3 | Introduction to Unsupervised and Representation Learning | Lecture 6 References: [DAYAN] Sect. 8.1-8.3 [PANINSKI] Sect 19.1, 19.2.1, 19.3.1, 19.3.2 |
| 10 | 11/04/16 (11.30-13.30) | SI 3 | Associative Memories I - Hopfield Networks | Lecture 7 References: [DAYAN] Sect. 7.4 (Associative Memory part) [PANINSKI] Sect. 17.1, 17.2 |
| 11 | 13/04/16 (15.30-18.30) | SI 3 | Lab 4 | Hebbian learning and Hopfield networks (Assignment 4) |
| 12 | 18/04/16 (11.30-13.30) | SI 3 | Associative Memories II - Stochastic networks and Boltzmann machines | Lecture 8 References: [DAYAN] Sect. 7.6 Further readings: [1] A clean and clear introduction to RBM |
| 13 | 20/04/16 (15.30-18.30) | SI 3 | Lab 5 | Boltzmann machines (Assignment 5) |
| 25/04/16 (11.30-13.30) | SI 3 | No class due to Italian national holiday | ||
| 27/04/16 (15.30-18.30) | SI 3 | No class | ||
| 14 | 02/05/16 (11.30-13.30) | SI 3 | Representation learning and deep learning models | Lecture 9 References: [DAYAN] Sect. 10.1 Further Readings: [2] A classic divulgative paper from the initiator of Deep Learning [3] Recent review paper [4] A freely available book on deep learning from Microsoft RC |
| 15 | 04/05/16 (15.30-18.30) | SI 3 | Lecture: Adaptive Resonance Theory (ART) Lab 6 | Lecture 10 Deep RBM (Optional Assignment 6) Futher Readings: A gentle introduction to ART networks (with coding examples) can be found here |
| 16 | 09/05/16 (11.30-13.30) | SI 3 | Introduction to RNN: tasks and basic models | Lecture and info multifiles |
| 17 | 11/05/16 (15.30-18.30) | SI 3 | Introduction to RNN: properties and taxonomy; intro to learning by BPTT | Lecture and info multifiles (also RNN learning) |
| 18 | 16/05/16 (11.30-13.30) | SI 3 | Introduction to RNN: learning by RTRL | Lecture and info multifiles (RNN learning) plus blackboard notes |
| 19 | 18/05/16 (15.30-18.30) | SI 3 | Introduction to RNN: LAB 1 - learning with IDNN and RNN | Info and assignment multifiles (see "RNN - Lab1" section) |
| 20 | 23/05/16 (11.30-13.30) | SI 3 | Introduction to RNN: Reservoir Computing | Lecture and info multifiles (ESN) |
| 21 | 25/05/16 (15.30-18.30) | SI 3 | Introduction to RNN: LAB 2 - learning with ESN | Info and assignment multifiles (see "RNN - Lab2" section). NEW: See also the new "Upgrade" section for further clarification |
bionics-engineering/computational-neuroscience/cns2016.txt · Ultima modifica: 21/02/2017 alle 16:25 (8 anni fa) da Davide Bacciu