[Talk Summary 9] The Next Frontier in AI: Unsupervised Learning


Yann LeCun, Director of AI Research at Facebook, and Silver Professor of Dara Science, Computer Science, Neural Science, and Electrical Engineering at New York University, held a talk about unsupervised learning, the next frontier in AI, on Friday, 2016/11/18 at CMU.

At the beginning of the talk, prof. LeCun introduced Neuroscience, supervised learning, deep learning, multi-layer neural nets, convolutional network architecture, very deep convNet architectures, Memory-augmented networks. He presented different kinds of application using machine learning such as image recognition and question answering. 

The main part of the talk presented by prof. LeCun was about obstacles to AI. The challenge of the next several years is to let machines learn from raw, unlabeled data, such as video or text. This is known as unsupervised learning. AI systems today do not possess "common sense", which humans and animals acquire by observing the world, acting in it, and understanding the physical constraints of it. 

To review approaches to unsupervised learning, prof. LeCun specified the architecture of an intelligent system.  The most important of AI systems is learning predictive forward models of the world because there are a lot of uncertainty. How can we deal with uncertainty is a topic of unsupervised learning. In more details, he presented energy-based unsupervised learning and stated that the best idea ever is adversarial training. In his opinion, adversarial training is the coolest idea in machine learning in the last ten year. Finally, He showed some work about image prediction and video prediction with adversarial training.


2016/11/28
McConomy Auditorium
Carnegie Mellon University

Comments

Post a Comment

Popular posts from this blog

Personalized Access to Scientific Publications: from Recommendation to Explanation

Dario De Nart, Felice Ferrara, and Carlo Tasso ( UMAP-2013 ) http://link.springer.com/chapter/10.1007/978-3-642-38844-6_26 In the paper “Personalized Access to Scientific Publications: from Recommendation to Explanation”, Dario De Nart et al. present a Recommender and Explanation System (RES) that is able to recommend scientific publication and show explanation to users.  In order to do recommendation, Dario De Nart et al., firstly, use the The Dikpe Keyphrase extraction algorithm introduced by Pudota (2010) to extract keyphrases from papers. Each keyphrase has a weight called keyphraseness that reveals the several lexical and statistical indicators exploited in the extraction process. Higher is the keyphraseness, more relevant is the KP. For each paper in the collection, they represent it as a conceptual graph. Each node in the graph is a term broken down from a KP. Two nodes are connected when they appear in the same KP. For instance, the KP “document retrieval” is split into tw
Read more

Personalized Social Search Based on the User’s Social Network

David Carmel et al. - IBM Research Lab in Haifa, Israel ( CIKM-2009 ) http://dl.acm.org/citation.cfm?doid=1645953.1646109 Personalizing the search process considers the searcher’s personal attributes & preferences so that the system is able to, for example, do personalized query expansion, re-rank the result list or filter presented information. However, few studies consider the preferences of the user’s related people in social network which can be utilized to enrich the user’s preferences. In the paper “Personalized Social Search Based on the User’s Social Network”, Carmel et al. presents a study that leverages both aforementioned information resources to improve social search, which is the search process over “social” data (e.g., documents or people) gathered from Web 2.0 applications. Particularly, they plan to re-rank search results by considering the relationships with other users in the searcher’s social network (SN). Firstly, Carmel et al. build user profiles from t
Read more

[Talk Summary 2] Dynamic Information Retrieval Model

Image
In this seminar, prof essor Grace Hui Yang presents a dynamic information retrieval model which helps users explore the information space in order to find out which documents are relevant and which aren't, satisfying their information need. The dynamic IR task aims to find relevant documents for a session of multiple queries. It happens when information needs are complex, vague, evolving, often containing multiple subtopics. A dynamic system is one which changes or adapts over time, based on a sequence of events. While static IR does not learn directly from users and the parameters are updated periodically, dynamic IR is developed from interactive IR which exploits users' feedback to give recommendation or improve the search result or optimize ranking, which is called dynamic ranking principle. But interactive IR just treat interaction independently and response to immediate feedback. Dynamic IR tries to optimize over all interaction, uses it for long term gain and models
Read more