Artificial Intelligence (NYU Paris, Fall 2020)
Image credit: Transhumanism and the Future of Humanity Frost & Sullivan
There are many cognitive tasks that people can do easily and almost unconsciously but that have proven extremely difficult to program on a computer. Artificial intelligence is the problem of developing computer systems that can carry out these tasks. We will focus on five central sections in AI: Problem solving (and search methods), Logical reasoning, reasoning in uncertainty, learning with neural networks and reinforcement learning, learning by mimicking nature. Finally, we will also spend some time discussing some of the main challenges in computer vision and natural language understanding/processing For each of the sections above, we will study how they can improve the behavior of an intelligent agent. We will study the set of skills associated to each section and the methods that can be designed for our agent to demonstrate or at least mimic those skills. The course will essentially consist in building an intelligent agent by gradually endowing this agent with more and more tools as we go through each of the sections above.
The course will also discuss some of the philosophical questions related to AI such as the Frame Problem of McCarthy and Hayes, The Mind Body problem, Searle’s “Chinese room” thought experiment, The Turing Test,…
The class will follow the structure
1. Lectures (introduction of the new material that will be needed during the lab sessions and for the assignements)
2. Programming (lab) sessions, (you have the opportunity to apply what you have learned during the lecture, and you can ask all the questions you want to make sure you understand everything before the assignement)
3. Assignments (You are given a new problem and you are evaluated on your ability to use the course material to solve this new problem)
Schedule and Classroom
Lecture: Monday/Wednesday, 12.30pm – 1.45pm, Room 401
Recitations: Wednesday 2.15pm – 3.45pm. Room 401
Office hour: Monday 2.15pm – 3.45pm
Reading List
Assignments policy
Except if explicitely stated otherwise, assignments are due at the beginning of each class.
Current (temporary) version of the notes: Lecture notes as well as the list of material for the Midterm and Final
Practice (theory) Questions for each exam can be found by clicking on those exams below
Exam : 60% of the grade (30% midterm, 30% final)
Assignments : 30 % of the grade (Tentative schedule below)
Final Project : 10 % of the grade (Tentative schedule below, List of suggestions, Poster guidelines)
The Github page for the class will be hosted at https://github.com/acosse/ArtificialIntelligenceFall2020/ and will be used for the lab and the assignments. You can also click on each “Lab” in the schedule below and this will re-direct you to the github page.
Tentative schedule:
Legend: Lab sessions are in green, Homeworks are in red (right side of the table), dates related to the project are in orange.
Week # | date | Topic | Assignements |
Week 1 | 08/31, 09/02 | General Intro. Critical and Philosophical perspectives, History, Part I, Part II |
Readings |
Week 2 | 09/07, 09/09 | Intelligent Agent, Search Methods (including informed/uninformed, A*,..) Part I Part III Lab 1 |
Readings, Solutions |
Week 3 | 09/14, 09/16 | Intelligent Agents, Search Methods (including informed/uninformed, A*,..) Part II Part IV, Part V Lab 2 |
Readings |
Week 4 | 09/21, 09/23 | Logical reasoning, Planning and acting (including first order and propositional Logic) (Part I) Part VI, Lab 3 |
Readings Solutions |
Week 5 | 09/28, 09/30 | Logical reasoning, Planning and acting (including first order and propositional Logic) (Part II), Part VII , Part IIX Lab 4 (Part I) / Solutions |
Readings |
Week 6 | 10/05, 10/07 | Learning, Neural Networks and Deep Learning (Part I) Part IX Lab 5, Partial Solutions |
Project choice Assign. 1 |
Week 7 | 10/12, 10/14 | Learning, Neural Networks and Deep Learning (Part II) Lab 6, Part X, Additional Note |
Readings |
Week 8 | 10/19, 10/21 | Unsupervised and Reinforcement Learning, Slides |
|
Week 9 | 10/26, 10/28 | Learning in multiagent systems + Guest lecture Lab 7 |
Readings |
Week 10 | 11/02, 11/04 | Learning under uncertainty, Bayesian Nets, Backward chaining | Assign. 3, Readings Solutions |
Week 11 | 11/09, 11/11 | Biology inspired computing (Evolutionary Algs, Particle Swarm, Ant Col.) (Part I) | |
Week 12 | 11/16, 11/18 | Biology inspired computing (Evolutionary Algs, Particle Swarm, Ant Col.) (Part II) | |
Week 13 | 11/23, 11/25 | Computer Vision and Language Processing (Part I), |
Assign. 4 |
Week 14 | 11/30, 11/02 | Computer Vision and Language Processing (Part II) | |
Week 15 | 12/07, 12/09 | Project/Paper Presentations |
- Artificial Intelligence: A Modern Approach, Russell, Norvig
- Artificial Intelligence, P. H. Winston
- Introduction to Artificial Intelligence, Mariusz Flasinski
- Artificial Intelligence: foundations of computational agents, Poole, Mackworth
Lab Sessions and programming policy
The lab sessions will require you to do some programming. It is strongly recommended to use python as it is more flexible and will be useful to you when moving to pytorch later on for more advanced machine learning methods requiring GPU processing.
Downloading and getting started with Python.
- Start by downloading anaconda: https://www.anaconda.com/download/#macos
- If you don’t have a text editor yet, you can download sublime text (see interesting keyboard shortcuts here)
Data sets can be downloaded on the following websites: