Entry requirements
Introduction to Psychology
Cognitive Psychology or Consciousness (or similar courses)
Description
Artificial Intelligence (AI) has become an important field of study and its techniques have found widespread implementation. The study of the brain plays an important role in this field because it can reveal how neural processes in the brain result in forms of intelligence such as pattern recognition. It can be expected that the influence of AI will increase in the coming years and decades, with potential effects also on work environments in psychology. This course gives a basic introduction into several aspects of AI, ranging from more traditional approach in AI (known as good old-fashioned AI or GOFAI) to ones inspired by neural processing in the brain (e.g. deep learning).
In the first part of the course, an introduction is given to the history of the field of artificial intelligence, and how it distinguishes itself from the related fields of computer science, psychology, and mathematics. Several graph traversal algorithms and heuristics (branch-and-bound, hill climbing) are discussed, as well as broadly applicable techniques such as backtracking. Also, the field of cognitive robotics is discussed, illustrating how implementing simple decision rules in a physical embodiment can create artificially intelligent robots.
Later in the course we will discuss pattern classification and recognition in neural networks (deep learning), based on a model of pattern classification and recognition in the brain. A number of topics and mathematical concepts will be discussed and presented. They include the concepts of information, frame of reference, pattern classification, vector representation, state space of a layer in a neural network, input space for a (neuron in a) network, perceptrons, linear separability and its relation to pattern classification, and unsupervised and supervised learning.
Course objectives
Students will acquire knowledge of:
aspects of the fields of artificial intelligence, robotics and neurocognition, and their potential influence on society and work environments (also in psychology);
examples of how complex behaviour and cognition emerges from different architectures of neural networks and forms of computation;
how neural networks can be trained;
basic analysis of forms of patterns classification.
Timetable
For the timetable of this course please refer to MyTimetable
Registration
NOTE As of the academic year 2021-2022, you must register for all courses in uSis. You do this twice a year: once for the courses you want to take in semester 1 and once for the courses you want to take in semester 2.
Registration for courses in the first semester is possible from July. Registration for courses in the first semester is possible from December.
The exact date on which the registration starts will be published on the website of the Student Service Center (SSC). First year Bachelor students as well as premaster students will be registered by the Student Service Center; they do not need to register themselves.
The registration period for all courses closes five calendar days before the start of the course.
Also read the complete registration procedure
Elective
Elective students have to enroll for each course separately. For admission requirements contact your study advisor.
Mode of instruction
The course consists of 8 2-hour lectures.
Assessment method
There is a written exam consisting of open questions. They are based on the literature and the lectures.
The Institute of Psychology uses fixed rules for grade calculation and compulsory attendance. It also follows the policy of the Faculty of Social and Behavioural Sciences to systematically check student papers for plagiarism with the help of software. Disciplinary measures will be taken when fraud is detected. Students are expected to be familiar with and understand the implications of these three policies.
Reading list
Articles from journals. The final list will be announced on the blackboard at the start of the course. An impression of articles that are used:
Oram, M.W. & Perrett, D. I. (1994). Modeling Visual Recognition From Neurobiological Constraints. Neural Networks, 7, 945-972.
DiCarlo, J. J. & Cox, D. D. (2007). Untangling invariant object recognition. Trends in Cognitive Sciences., 11, 333-341.
Turing, A. M. (1950). Computing machinery and intelligence. Mind, LIX, 236, 433-460.
McClelland, J. L. (2009). Is a machine realization of truly human-like intelligence achievable? Cognitive Computation, 1, 17-21.
Contact information
- Dr. ir. Roy de Kleijn kleijnrde@fsw.leidenuniv.nl