PUBLIC MARKS with tags workshop & workshop

workshop from Sunny Tech conference

A workshop with Mark Geyer Wednesday, November 12, 2014

About [OR]EDU ONLINE EDUCATION IN VISUAL STORYTELLING [OR]EDU is an innovative online educational initiative focused on visual storytelling launched by the Objective Reality Foundation in 2008. The project offers free online workshops in photography and multimedia, as well as resources on the practice of the market, educational and project opportunities, contests and grants. Taught by international photographers and media professionals the workshops focus on the need to develop and maintain a personal vision, and to effectively market that vision as a product. Originally targeted at the talented young photographers and students from Russia and the CIS the project is expanding in two directions: geography and diversity of our community. In 2010-2011 we are taking [OR]EDU to the international level and introducing new comprehensive online educational events to support contemporary narrative and engage the public in navigating the wide range of social issues through visual storytelling.

Functioning Form: Merging medium and message in interface design, the user experience design process, Web applications, and more.

Comment bien gérer un workshop

Exemple d'utilisation de Mindmanager pour un workshop IA avec un client

Theoretical results strongly suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g. in vision, language, and other AI-level tasks), one may need "deep architectures", which are composed of multiple levels of non-linear operations (such as in neural nets with many hidden layers). Searching the parameter space of deep architectures is a difficult optimization task, but learning algorithms (e.g. Deep Belief Networks) have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. This workshop is intended to bring together researchers interested in the question of deep learning in order to review the current algorithms' principles and successes, but also to identify the challenges, and to formulate promising directions of investigation. Besides the algorithms themselves, there are many fundamental questions that need to be addressed: What would be a good formalization of deep learning? What new ideas could be exploited to make further inroads to that difficult optimization problem? What makes a good high-level representation or abstraction? What type of problem is deep learning appropriate for? The workshop presentation page show selected links to relevant papers (PDF) on the topic.