SC:Knowledge Engineering

From Chrome
Revision as of 07:30, 11 June 2012 by Matteo (Talk | contribs) (Course Program and Schedule)

Jump to: navigation, search


The following are last minute news you should be aware of ;-)

 12/03/2012: The course starts today! The schedule has already changed to reduce overlaps

Course Aim & Organization

The course introduces the general principles of Artificial Intelligence and its applications. Two approaches to model building and knowledge representation will be presented: the traditional one, based on symbolic representation of knowledge (e.g., frames, rules, fuzzy logic, ...), and one inspired to biological models (e.g., neural networks and genetic algorithms).

Teachers

The course is composed by a blending of lectures and exercises by the course teacher and the teaching assistant.

Course Program and Schedule

Lectures will cover the following topics:

  • Artificial intelligence: problems, approaches and applications
  • Models for knowledge representation biologically inspired and adaptive models.
  • Machine Learning: supervised methods, unsupervised methods, reinforcement learning.
  • Artificial Neural Networks and Genetic Algorithms.
  • Knowledge representation techniques: semantic networks, frames, objects, production rules.
  • Uncertainty and approximate knowledge representation. Fuzzy systems.
  • Knowledge engineering: methods to develop knowledge based systems.
  • Knowledge acquisition, conceptualization and modeling.

Lectures are on:

  • Monday 8:15-10:15 in room A3.8
  • Tuesday 8:15-10:15 in room A4.1

A detailed schedule of the course can be found here; topics are just indicative while days and teachers are correct up to some last minute change (I will notify you by email). Please note that not all Tuesdays and Wednesdays are in!!

Date Day Time Room Teacher Topic
12/03/2012 Monday 08:15 - 10:15 3.8 Matteo Matteucci Course introduction: from artificial intelligence to natural computation
13/03/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Useful background: Maximum Likelihood Estimation and Gradient descent optimization
19/03/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
20/03/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Introduction to neaural networks, the biologic neuron, the perceptron model
26/03/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
27/03/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Hebbian learning, Perceptron learning exercise, the XOR problem
02/04/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
03/04/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Feed forward neural networks: backpropagation
16/04/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
17/04/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Demo and derivation of squared error function
23/04/2012 Monday 08:15 - 10:15 No lecture today!
24/04/2012 Tuesday 08:15 - 10:15 No lecture today!
07/05/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
08/05/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Cross Entropy error function, Overfitting, Crossvalidation techniques, Early stoppig
14/05/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
15/05/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Early Stopping and Weight Deacy
21/05/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
22/05/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Recurrent Architectures
28/05/2012 Monday 08:15 - 10:15 3.8 Andrea Bonarini ...
29/05/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Radial Basis Functions
04/06/2012 Monday 08:15 - 10:15 3.8 Matteo Matteucci Neuro Fuzzy Systems
05/06/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci Introduction to Genetic Algoritmhs
11/06/2012 Monday 08:15 - 10:15 3.6 Matteo Matteucci Genetic Algorithms: conding and operators
12/06/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci ...
18/06/2012 Monday 08:15 - 10:15 3.6 Matteo Matteucci ...
19/06/2012 Tuesday 08:15 - 10:15 4.1 Matteo Matteucci ...

Course Evaluation

The course evaluation is performed by a written exam divided in two parts (lasting usually 2.5 hours in total):

  1. Topics covered by the course teacher during the course
  2. Topics covered by the teaching assistant during the course

Each part will score 16/32 and the exam is passed if the sum of the two parts, after rounding, is at least 18.

As a reference for the exam format you can have a look at the following material from KE:

or from the Italian version (Ingegneria della Conoscenza):

Teaching Material

The textbooks used for the course are:

In the following you can find the lecture slides used by the teacher and the teaching assistant during classes. Some additional material that could be used to prepare the oral examination is provided as well.

Neural Networks and Evolutionary Computation

Knowledge Engineering

Uncertainty management and Fuzzy systems

Additional Lectures to complement Slides and Textbooks

  • Appunti (bigino): these are notes taken in the past by some students of mine ... they are in Italian!