[Debian-med-packaging] ACDL 2019 Titles & Abstracts (Part 1) Advanced Course on Data Science & Machine Learning 2019 - Application Deadline: March 31

[ICAS]

ACDL 2019, 2nd Advanced Course on Data Science & Machine Learning @ Certosa di Pontignano, Siena, Italy, July 15-19, 2019
https://acdl2019.icas.xyz 
Early registration deadline: March 31
https://acdl2019.icas.xyz/registration/
Each Lecturer will hold three lessons on a specific topic.
Ioannis Antonoglou, Google DeepMind, UK
Phillip Isola, MIT, USA 
Leslie Kaelbling, MIT - Computer Science & Artificial Intelligence Lab, USA 
Ruslan Salakhutdinov, Carnegie Mellon University & AI Research at Apple, USA
Josh Tenenbaum, MIT, USA
Naftali Tishby, Hebrew University, Israel
Joaquin Vanschoren, Eindhoven University of Technology, The Netherlands
Oriol Vinyals, Google DeepMind, UK

Email not displaying correctly? View it https://sg-mktg.com/MTU1Mzc2NDc1Nnw1WXY0SVdBeGM2XzVCUE0yeWV4STg5R0lHdDZIQjRFZ0ticnZEZWlmcU1oVmlIeThLX2s2a1FQUjlQSFhzNGQwY2E0cU9MRkZhRWhkNWJJTkNUZWNOS1FpWHpFNEFPZFJVdWM1MFNJS3VnRGRqVmJQMi1xZ183UUhscm8zRmUySmZVMXpwbUdjazBWcGFaaVVaV0lwSXRqZl8zRC1IUllfU09BWWExWGlhQTFSNnlGOWNxVzJUVWxRY2V6SlNwRmRfQ3F3aVR4WHVSX1BZN1c1US0tYUpORzVRRW5nNlFJWTVkMHZOTDhXb2RKVG4xR2JKbzFPbzltenE1X1R3dTQyczh6YjNWN3YtdlR4QmlpaTFvRUY0a2k1SUQ3Sk16NkdCR3VzUW5ib0RRPT18gDy_psjX1bbEL_o76wNLcwFNRR6nqoq_pdN00QFK0Po= in your browser.

https://www.facebook.com/groups/204310640474650/

https://twitter.com/TaoSciences

* Apologies for multiple copies. Please forward to anybody who might be interested *

Dear All,

it follows the first titles (and abstracts, a little further down in this email) of the ACDL 2019 Lectures https://acdl2019.icas.xyz/lecturers/.

Phillip Isola - MIT, USA

Lecture 1: Introduction to Generative Adversarial Networks

Lecture 2: Conditional GANs and Data Prediction

Lecture 3: GANs for Domain Translation

Leslie Kaelbling - MIT - Computer Science & Artificial Intelligence Lab, USA #

Lecture 1: Learning in the factory and in the wild: designing robot systems that learn

Lecture 2: Learning factored transition models for planning in complex hybrid spaces

Lecture 3: Learning to speed up planning in complex hybrid spaces

Ruslan Salakhutdinov - Carnegie Mellon University & AI Research at Apple, USA

Lecture 1: Introduction to Deep Learning, Neural Networks & Convolutional Neural Networks

Lecture 2: Deep Unsupervised Learning

Lecture 3: Recent Advances and New Challenges for Deep Learning

Lecture 4: Deep Learning for Natural Language Processing/Reading Comprehension

Soon we will publish the titles and the abstracts of the other ACDL 2019 lectures https://acdl2019.icas.xyz.

Hopefully see you in Siena in July!

ACDL Organizing Committee.

* Apologies for multiple copies. Please forward to anybody who might be interested *

ACDL 2019, 2nd Advanced Course on Data Science & Machine Learning @ Certosa di Pontignano, Siena, Italy, July 15-19, 2019 https://acdl2019.icas.xyz

https://acdl2019.icas.xyz       https://acdl2019.icas.xyz

Early registration deadline: March 31
https://acdl2019.icas.xyz/registration/ https://acdl2019.icas.xyz/registration/

Each Lecturer will hold three lessons on a specific topic.

Ioannis Antonoglou, Google DeepMind, UK

Marco Gori, University of Siena, Italy

Phillip Isola, MIT, USA                        

Leslie Kaelbling, MIT - Computer Science & Artificial Intelligence Lab, USA

Ilias S. Kotsireas, Wilfrid Laurier University, Canada 

Dolores Romero Morales, Copenhagen Business School, Denmark            

Panos Pardalos, University of Florida, USA

Ruslan Salakhutdinov, Carnegie Mellon University & AI Research at Apple, USA

Josh Tenenbaum, MIT, USA

Naftali Tishby, Hebrew University, Israel

Joaquin Vanschoren, Eindhoven University of Technology, The Netherlands

Oriol Vinyals, Google DeepMind, UK  

https://acdl2019.icas.xyz   https://acdl2019.icas.xyz

Best,

ACDL 2019 Organizing Committee. 

* Apologies for multiple copies. Please forward to anybody who might be interested *

ACDL 2019 Registration https://acdl2019.icas.xyz/registration/

Phillip Isola

MIT, USA

Lecture 1: Learning in the factory and in the wild: designing robot systems that learn 

We examine the general problem of designing robot systems from a decision-theoretic perspective that makes it clear when an individual needs to learn when it is actually performing its tasks (in the wild) and when the AI engineers need to use learning methods to design a good robot learner. We will examine several learning paradigms from this perspective and talk about methods for meta-learning, including modular meta-learning and graph element networks.

Lecture 2: Learning factored transition models for planning in complex hybrid spaces 

Many robotics problem distributions are better addressed by learning models and using them to do online reasoning (an approach also known as model-predictive control) than by learning a policy or value function. We begin by discussing this claim, and then study the forms of models that are most appropriate for different types of planning problems. We then examine two new approaches for learning models that are appropriate for planning in complex hybrid (mixed discrete and continuous) problems, such as robot task and motion planning. One approach is based on Gaussian-process active learning and another on an extension of graph neural networks. 

Lecture 3: Learning to speed up planning in complex hybrid spaces 

An important role for learning is to speed up search: this is the critical role that learning plays in methods such as Alpha-Zero. We will examine several different mechanisms that can be used (including learning heuristic or static evaluation functions and learning to bias the action sampling distribution), with a focus on problems that require choosing actions from a continuous or hybrid space.

Leslie Kaelbling

MIT - Computer Science & Artificial Intelligence Lab, USA #

Lecture 1: Learning in the factory and in the wild: designing robot systems that learn 

We examine the general problem of designing robot systems from a decision-theoretic perspective that makes it clear when an individual needs to learn when it is actually performing its tasks (in the wild) and when the AI engineers need to use learning methods to design a good robot learner. We will examine several learning paradigms from this perspective and talk about methods for meta-learning, including modular meta-learning and graph element networks.

Lecture 2: Learning factored transition models for planning in complex hybrid spaces 

Many robotics problem distributions are better addressed by learning models and using them to do online reasoning (an approach also known as model-predictive control) than by learning a policy or value function. We begin by discussing this claim, and then study the forms of models that are most appropriate for different types of planning problems. We then examine two new approaches for learning models that are appropriate for planning in complex hybrid (mixed discrete and continuous) problems, such as robot task and motion planning. One approach is based on Gaussian-process active learning and another on an extension of graph neural networks.

Lecture 3: Learning to speed up planning in complex hybrid spaces 

An important role for learning is to speed up search: this is the critical role that learning plays in methods such as Alpha-Zero. We will examine several different mechanisms that can be used (including learning heuristic or static evaluation functions and learning to bias the action sampling distribution), with a focus on problems that require choosing actions from a continuous or hybrid space.

Unsubscribe https://u9436285.ct.sendgrid.net/asm/unsubscribe/?user_id=9436285&data=_CeQwqrsPwQpI-aWcf0Py7gvWn03x9oAvM-M-17Z7BWw_E35COUnE31EMLJsdQlZOsfIWnln99puZhRoERU2DQP67MHOZ6j1hDLkuxfykAbo0tD6HnnoJQ5BLN99PaLfYLGojgGEL90iI9zu4yucCqa8iAfp05htspuB0_wQOW6KxkQOsbf17KPjaaEZ1xNNKQ5KiDE_ybqXuUKJxAQI08d03ySNH4jf2AMjPt3tjzKU1Mh3fGJMMuwzRyM1lrXf1tPr2esJzIPQ7wxOd_d3zO8wBT7OZGaq0ur2nF3MZqIjrERVhwiniYKuyOkzwkrtmI5UvFyliTe3qHDmUFk6s-KZHCo2X1DOfurHp8NrI3oAxR51hNB4fkG7uTDP0op_dcCCnJlnsPaYBvy6FHx-Orw1v5nVrD9WEm5vuHPuDoi0ptfEwZV4R4_2l1LfGxaKwHmplKqOyRBuHKPGpSHZhbhDQVy2FXTwuEEPDjGfmTuqrhws3ZKXldzizmIIb5NR4RTG5rOgMoYe0M-nsMFqviLKXi1za1Y3V6ao1y25WVDtvohJ8oJFWakLke5zYiHJJvGdBhcijXL-uhLaeBIU6kfEzHiN_7d9hkw1sIAQkwyiShLsMJOzUf5WDFU6qZ_C | Update Preferences https://u9436285.ct.sendgrid.net/asm/?user_id=9436285&data=DPWR3LpAKLI-MOZteNrvBZyDc25lwBt5ojcEWg5Hc_3vnnjDPi3U1nc6UqmIKYtM2YSme7SNY_ISUd0k4tfk9BXeWvzNq9L3mrt0nhimDhoDbI6GsiC7Wy0XGrwuPj9R650MyzKZk4s5aIJPxAuzUwJUJriD1oKtG_EWeXFAFQWIzwaBfB7PGBX9WoN0LfSXWsLPks04Mgp88lHNx3MSNzb6EXePZDfqqz9Uo0YTJmALdENgT04ljRR6JtgdDG_JwgvKyDhEJu-JB0LqeiN_GA0Ucf5DzVa6uRj0bJGsNwG6LN_TRsiiZTLMLeDQqQ3qmagogJLMvPOrY3APUnlQBAC_6GTamTXdDo0rdGpPFNUlU5JaYX-Nx0rGoCBCtiGoNiDVjn52SoSfix2MS2a8bz70nwkkWKxZIRhiD0Ag0kyknyR7TjoLEcTUQY3rKhtnJ_K8RtaRbnTAyG8Qnz7u1LN-prNtxekvAoUHqqUhWdEq0_V7uM5w3-ZdzakGlke9v1ao68blEtr6y15icgeXdhJ2ulpabUzp-1VXJxROINmAGPd47nITYf6yZrZgH2bvaFPjvNL9eH8IKyrpWN-jsF0VQw2KodCzn_SvO5LEvFg=

ICAS

Certosa di Pontignano - Loc. Pontignano, 5   

Castelnuovo Berardenga (Siena),  53019
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://alioth-lists.debian.net/pipermail/debian-med-packaging/attachments/20190328/b7408cb0/attachment-0001.html>