Prof. Dancy's Site

Bucknell CSCI 379 - Introduction to AI & Cognitive Science, Fall 2019

Introduction to Artificial Intelligence and Cognitive Science: Building Artificial Minds

Prof. Christopher L. Dancy

Office: Dana 340

Phone: 570.577.1907

Office Hours: M 2-3:30pm, Th 2-3:30pm - My calendar

The full syllabus can be found here

A tentative course schedule can be found here

Course Overview

How can we build artificial minds? What do we need to represent and how do we represent it? How can we make them learn, and perceive in an environment? How can we use the way people think to design these minds? What about the environment, how should it affect an intelligent agent?

In this course, I will give you some tools to provide some answers to these questions. Ultimately, as with most endeavors this difficult, we will come up short. But fear not! You will have an opportunity to explore past answers to these questions and learn from them. Furthermore you will have an opportunity to use the thinking, techniques, and tools you learn in this course and in the future!

This course will not provide full coverage of AI and Cognitive Science for this would almost certainly be impossible given the time! These fields are big with many theories, subfields, and applications. This course will focus on the AI approach that thinks the way people think. (Though, thankfully no one will create anything close to the Ava in "Ex Machina"!)

Course Assignments:

Unless otherwise specified, a due date means due on that date by 11:59pm

Design an AI Due: 6-Sept beginning of class

RBES Design an AI Due: 13-Sept beginning of class

RBES Vacuum Agent Due: 18-Sept

Neural Networks Assignment Phase 1 Due: 27-Sep, Phase 2 (Final) Due: 06-Oct

Heuristic tree Assignment #1 Due: 25-October

Q-Learning Assignment Due: 18-November

Maze Sim Extra Credit Due: 09-December

Course Projects:

Midterm Project Check writeup for due dates!

Final Project Check writeup for due dates!

Small extras:

General Design AI worksheet (Goals, Environment, Adaptation)

CNN example

Local Tree Search example

Q Learning example