-
Neural Systems Modeling Ch10-13 Master Tool
Tools | 02 Aug 2013 | Contributor(s):: Jessica S Johnson, NanoBio Node
Combination of all tools used in Chapters 10-13 of Neural Systems Modeling by Anastasio
-
[Illinois] MCB 493 Lecture 10: Time Series Learning and Nonlinear Signal Processing
Online Presentations | 24 Oct 2013 | Contributor(s):: Thomas J. Anastasio
-
[Illinois] MCB 493 Lecture 11: Temporal-Difference Learning and Reward Prediction
Online Presentations | 18 Jul 2013 | Contributor(s):: Thomas J. Anastasio
Temporal-difference learning can train neural networks to estimate the future value of a current state and simulate the responses of neurons involved in reward processing.
-
[Illinois] MCB 493 Lecture 13: Predictor-Corrector Models and Probabilistic Inference
Online Presentations | 24 Oct 2013 | Contributor(s):: Thomas J. Anastasio
-
[Illinois] MCB 493 Lecture 14: Future Directions in Neural Systems Modeling
Online Presentations | 18 Jul 2013 | Contributor(s):: Thomas J. Anastasio
In the future, neural systems models will become increasingly complex and will span levels from molecular interactions within neurons to interactions between networks
-
[Illinois] MCB 493 Lecture 2: Recurrent Connections and Simple Neural Circuits
Online Presentations | 03 Feb 2013 | Contributor(s):: Thomas J. Anastasio
Networks with recurrent connections, forming circuits, and containing only a few neural units can shape signals in time, produce oscillations, and simulate certain forms of low-level motor control.
-
[Illinois] MCB 493 Lecture 4: Covariation Learning and Auto-Associative Memory
Online Presentations | 21 Feb 2013 | Contributor(s):: Thomas J. Anastasio
Networks with recurrent connection weights that reflect the covariation between pattern elements can dynamically recall patterns and simulate certain forms of memory.
-
[Illinois] MCB 493 Lecture 5: Unsupervised Learning and Distributed Representations
Online Presentations | 21 Feb 2013 | Contributor(s):: Thomas J. Anastasio
Unsupervised learning algorithms, given only a set of input patterns, can train neural networks to form distributed representations of those patterns that resemble brain maps.
-
[Illinois] MCB 493 Lecture 6: Supervised Learning and Non-Uniform Representations
Online Presentations | 25 Feb 2013 | Contributor(s):: Thomas J. Anastasio
Supervised learning algorithms can train neural networks to associate patterns and simulate the non-uniform distributed representations found in many brain regions.
-
[Illinois] MCB 493 Lecture 7: Reinforcement Learning and Associative Conditioning
Online Presentations | 03 Jul 2013 | Contributor(s):: Thomas J. Anastasio
Reinforcement learning algorithms can simulate certain types of associative conditioning and train neural networks to form non-uniform distributed representations.
-
[Illinois] MCB 493 Lecture 8: Information Transmission and Unsupervised Learning
Online Presentations | 03 Jul 2013 | Contributor(s):: Thomas J. Anastasio
Unsupervised learning algorithms can train neural networks to increase the amount of information they contain about their inputs and simulate the properties of sensory neurons.
-
[Illinois] MCB 493 Lecture 9: Probability Estimation and Supervised Learning
Online Presentations | 03 Jul 2013 | Contributor(s):: Thomas J. Anastasio
Supervised learning algorithms can train neural units and networks to estimate probabilities and simulate the responses of neurons to multisensory stimulation.
-
[Illinois]: Avoidance Learn Simulation
Tools | 20 Jun 2013 | Contributor(s):: AbderRahman N Sobh, NanoBio Node, Jessica S Johnson
This script simulates avoidance conditioning as reinforcement learning with two upper motoneurons (SUMO and FUMO).
-
[Illinois]: Avoidance Learn Simulation with 'Call' Neuron
Tools | 25 Jun 2013 | Contributor(s):: AbderRahman N Sobh, NanoBio Node, Jessica S Johnson
This script simulates avoidance learning as a reinforcement learning with two upper motoneurons (sumo and fumo) and one "call" neuron.
-
[Illinois]: Error Gradient Estimations Due to Parallel Perturbation of Weights
Tools | 07 Jul 2013 | Contributor(s):: AbderRahman N Sobh, Jessica S Johnson, NanoBio Node
This tool trains two-layered networks of sigmoidal units to associate patterns using simultaneous perturbation of weights.
-
[Illinois]: Error Gradient Estimations Due to Perturbation of One Weight at a Time
Tools | 29 Jun 2013 | Contributor(s):: AbderRahman N Sobh, Jessica S Johnson, NanoBio Node
This tool trains two-layered networks of sigmoidal units to associate patterns using perturbation of one weight at a time.
-
[Illinois]: Neural Systems Modeling Ch 6-9 Master Tool
Tools | 26 Jul 2013 | Contributor(s):: Jessica S Johnson, NanoBio Node
Combination of all tools used in Chapters 6-9 of Neural Systems Modeling by Anastasio
-
[Illinois]: Optimize Connectivity Profile of Activity-Bubble Network
Tools | 25 Jun 2013 | Contributor(s):: Jessica S Johnson, NanoBio Node
Use genetic algorithm with binary chromosomes to optimize activity-bubble network.
-
[Illinois]: Perturbative Reinforcement Learning to Develop Distributed Representations
Tools | 10 Jul 2013 | Contributor(s):: AbderRahman N Sobh, Jessica S Johnson, NanoBio Node
This tool trains three-layered networks of sigmoidal units to associate patterns.
-
[Illinois]: Perturbative Reinforcement Learning Using Directed Drift
Tools | 10 Jul 2013 | Contributor(s):: AbderRahman N Sobh, Jessica S Johnson, NanoBio Node
This tool trains two-layered networks of sigmoidal units to associate patterns using a real-valued adaptation of the directed drift algorithm.