CISC/CMPE 452/COGS 400 Neural and Genetic Computing
Overview
The course will walk you throug h the realm of Artificial Neural Networks (ANN) and
Cognitive Modeling. Unlike courses where you only learn to use existing tools and
predefined functions to implement a model, in this course you will have to understand
the mathematics behind computational modeling. You will learn how ANNs are
modeled based on the structure and functionality of brain neurons, how they are
constructed, how they learn from data, and how the technology can be used to develop
machine intelligence for real life applications. You will have to program ANNs from
scratch without using existing functions, and need background knowledge of linear
algebra (https://ecampusontario.pressbooks.pub/linearalgebrautm/chapter/chapter-2-
matrix-algebra/). You will go through some tutorials organized by the TAs
(https://www.tensorflow.org/tutorials/quickstart/beginner) and learn to build simple
ANN models which would evolve into more complicated models. Finally, you will
download, modify and execute a deep learning model as a group to see how models can
be developed to real life problems. Since models learn from data, there are three main
phases in the model development.
1. Data Preprocessing to prepare the data to be fed into the machine learning (ML)
model,
2. Model Training to learn to extract key features from the data or patterns for
certain task
3. Apply the learned knowledge for cognition and decision making
Pre-requisites
Required courses: Machine Learning; Multivariable Calculus; Linear Algebra;
Probability & Statistics. Pre-requi site courses include Linear Algebra, CISC 235/3.0 or
ELEC 278/3.0, and programming experience. Recommended knowledge: Any of the COGS
courses (100 or 201) or PSYC 100 or PSYC 221 or PHIL 270.
Readings
There is no required textbook for the class. Here are some references that can be used:
1. Charu C. Aggarwal. Neural Networks and Deep Learning: A Textbook. Springer,
2018.
2. Zhang, Aston and Lipton, Zachary C. and Li, Mu and Smola , Alexander J, “Dive
into Deep Learning”, arXiv:2106.11342, 2021, https://d2l.ai/
3. Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka. Elements of Neural
Networks. MIT Press, 1997.
