AI : A Modern Approach

3 Members
study group for the book AI : A Modern Approach1 Servers

Load older messages

Timestamp Message
9 Jul 2016
02:43:49@suriyadeepan:matrix.orgsuriyadeepanA short course on Intro to AI by Norvig and Thrun https://www.udacity.com/course/intro-to-artificial-intelligence--cs271
16 Aug 2016
13:04:53@suriyadeepan:matrix.orgsuriyadeepan changed their profile picture.
22 Sep 2016
16:14:18@vwpfong:matrix.orgVincent joined the room.
6 Oct 2016
07:30:35@vwpfong:matrix.orgVincent set their display name to Vincent.
27 Nov 2016
09:03:05@vwpfong:matrix.orgVincent set a profile picture.
4 Dec 2016
15:25:36@suriyadeepan:matrix.orgsuriyadeepan changed their profile picture.
25 Jan 2017
10:16:07@suriyadeepan:matrix.orgsuriyadeepan changed their profile picture.
4 Feb 2017
05:05:43@Spacex:matrix.org@Spacex:matrix.org joined the room.
5 Feb 2017
16:29:44@Spacex:matrix.org@Spacex:matrix.org I used to teach the book
16:32:20@vwpfong:matrix.orgVincentAny expert in language model?
16:32:43@Spacex:matrix.org@Spacex:matrix.org Certainly
16:34:24@Spacex:matrix.org@Spacex:matrix.org HMM for example
16:37:13@vwpfong:matrix.orgVincentWell, do u think deep learning models are the solution to text comprehension?
16:37:59@vwpfong:matrix.orgVincentA lot of experts think natural language understanding is not probabilistic
16:39:07@vwpfong:matrix.orgVincent For example, Lstm rnn is just a sequence mapping function so it can't understand the meaning without the context
16:39:31@vwpfong:matrix.orgVincentHence, it is only for simple translation only.
16:41:13@suriyadeepan:matrix.orgsuriyadeepanthere are complex models built with lstm that considers context, while decoding/answering/generating
16:48:52@Spacex:matrix.org@Spacex:matrix.org I think pure engineering techniques and probability models have already failed to solve the core of natural languages complex problem ..the use of phoneme is the main issue for the failure of previous systems and will not allow more progress toward understanding / cognition or the creation of a complete intelligent agent
16:51:06@vwpfong:matrix.orgVincentI heard that semantic network is a major breakdown in this area
16:51:37@vwpfong:matrix.orgVincent It will solve the issue deep learning can't for language
16:53:17@Spacex:matrix.org@Spacex:matrix.org Deep learning has made good progress so far but I need the knowledge representation part has not been deeply discussed
16:54:08@Spacex:matrix.org@Spacex:matrix.org Thank you Vincent you just indicated one problem
16:57:50@Spacex:matrix.org@Spacex:matrix.org When it comes to language understanding .. Design is the main goal
25 Feb 2017
03:14:06@suriyadeepan:matrix.orgsuriyadeepan changed their profile picture.
10 Mar 2017
09:13:36@suriyadeepan:matrix.orgsuriyadeepan changed their display name from suriyadeepan to paarulakan(பாருலகன்).
09:14:18@suriyadeepan:matrix.orgsuriyadeepan changed their display name from paarulakan(பாருலகன்) to suriyadeepan.
2 Feb 2018
09:34:28@suriyadeepan:matrix.orgsuriyadeepan removed their profile picture.
09:35:58@suriyadeepan:matrix.orgsuriyadeepan set a profile picture.
8 Jul 2018
02:58:29@suriyadeepan:matrix.orgsuriyadeepan changed their profile picture.

There are no newer messages yet.

Back to Room List