Introduction to theory of neural computation starting from simple units to complex network topologies with emphasis on biological learning and biologically inspired learning (neural networks). Topics include basic mathematical models of biological computing with a single protein, a single neuron, multiple neurons, and biologically- inspired computing with perceptrons, Hopfield networks, Boltzmann machines, multilayer neural networks, and convolutional “deep” networks. Additional topics include computational tradeoffs between Hodgkin -Huxley, integrate -and- fire, and Itzkovich models, synaptic plasticity, receptive field design and organization, and mechanisms for supervised and unsupervised learning.
Prerequisites: python programming, calculus, linear algebra, and basic probability theory, or consent of instructor.
You Will Learn
- Biological Computing: Protein Computation and Bistable Systems
- Biological Computing: Single Neuron Modeling with emphasis on computational tradeoffs between Hodgkin-Huxley, integrate-and-fire, and Itzkovich models
- Biological Computing: Synaptic Plasticity and Receptive Field Modeling
- Biologically-Inspired Computing: Perceptrons, Boltzmann machines
- Biologically-Inspired Computing: Hopfield networks, Restricted Boltzmann machines, and Multilayer neural networks
- Biologically-Inspired Computing: Convolutional “Deep” Networks
To view other workshop descriptions, or to get general information about the 2016 ICME Summer Workshop Series, click here.
ICME Summer Workshops are open to participants 18 years and older. If you are under the age of 18 and would like to participate, please contact email@example.com.
Please contact the Program Team at