https://mw.hh.se/caisr/index.php?action=history&feed=atom&title=Internal%2FTeaching_AI 2026-04-04T04:01:59Z Revision history for this page on the wiki MediaWiki 1.35.13 https://mw.hh.se/caisr/index.php?title=Internal/Teaching_AI&diff=1799&oldid=prev 2014-10-15T07:56:18Z

<p>Created page with &quot;== Project == Keep Java server, strongly recommend they write players in Python - test the connectivity Setup network environment to run the server. Can it be r2s server or ...&quot;</p> <p><b>New page</b></p><div>== Project ==<br /> <br /> Keep Java server, strongly recommend they write players in Python - test the connectivity<br /> <br /> Setup network environment to run the server. Can it be r2s server or a virtual machine on the wiki server (talk with Nicholas)?<br /> <br /> == Labs ==<br /> <br /> * Lab1:<br /> ** reflex agent, using rule-based reasoning engine<br /> *** let&#039;s try &lt;code&gt;pyke&lt;/code&gt;<br /> *** create 2-3 simple examples<br /> ** simple mobile robot controller<br /> *** let&#039;s try Webots http://www.cyberbotics.com/overview<br /> *** we either create our own world, or we use one of the competitions: the rat maze or the savanna world<br /> *** the trick is to have individual decisions be complex enough (we don&#039;t want to have too much memory yet)<br /> *** make sure Webots is easy to integrate with pyke!<br /> ** simple poker player<br /> *** demonstrate how to stratify the knowledge (levels of hand quality, evaluate opponents, etc.)<br /> *** how easy is it to calculate winning percentage of any given hand in pyke?<br /> <br /> * Lab 2: <br /> ** search algorighms: A*<br /> ** mobile robot path planning<br /> *** can we make it a car instead of omnidirectional robot?<br /> *** talk to Jennifer/Gaurav about ideas?<br /> *** do it in an abstract manner<br /> *** but maybe we could connect to Webots later for visualisation?<br /> ** poker bidding against known hand &amp; strategy<br /> *** we need to come up with sufficiently complicated strategy!<br /> *** has to have a number of local minima<br /> *** and a number of reasonable heuristics<br /> <br /> * Lab3<br /> ** logic<br /> *** students write knowledge base in FOL<br /> *** the idea is to &quot;do machine learning by hand&quot; - come up with some rules, see which examples are covered, iterate<br /> ** human behaviour analysis and anomaly detection<br /> *** based on data from Jens<br /> *** generated by his simulator<br /> *** KB should explain as many examples as possible<br /> ** poker: deduce opponent&#039;s hand<br /> *** based on known cards<br /> *** and description of their strategy<br /> <br /> * Lab 4<br /> ** Bayesian networks<br /> ** healthcare and medical diagnosis<br /> *** match symptoms with causes<br /> *** talk to Anita and Nicholas<br /> ** poker: opponent recognition<br /> *** given non-deterministic strategies, match play history to an opponent<br /> <br /> * Lab 5<br /> ** Learning <br /> *** SVM, neural networks and/or decision trees<br /> ** fingerprint classification (?)<br /> *** talk with Anna (?)<br /> *** maybe face / digit recognition (talk with Stefan K)<br /> ** poker: learn opponent&#039;s strategy<br /> *** train on past games<br /> *** try to predict next bids<br /> *** how to deal with hidden information (current hand)?</div>

Slawek