Full Program

Arrival: July 14, 2019

7:30 - 9:00
Breakfast

9:00 - 9:50
Lecture 1
Josh Tenenbaum

9:50 - 10:40
Lecture 1: Learning in the factory and in the wild: designing robot systems that learn
Leslie Kaelbling

10:40 - 11:20
Coffee Break

11:20 - 12:10
Lecture 1: Introduction to Generative Adversarial Networks
Phillip Isola

12:10 - 13:00
Lecture 1: Model-based reinforcement learning I
Ioannis Antonoglou

13:00 - 15:00
Lunch

15:00 - 15:50
Lecture 1: Unsupervised Learning: Learning Deep Generative Models
Ruslan Salakhutdinov

15:50 - 16:40
Lecture 2: Deep Learning for Natural Language Processing/Reading Comprehension
Ruslan Salakhutdinov

16:40 - 17:20
Coffee Break & Group Photo

17:20 - 18:10
Lecture 1: Introduction to Automated Machine Learning (AutoML)
Joaquin Vanschoren

18:10 - 19:30
Poster Session

19:30 - 21:30
Dinner

7:30 - 9:00
Breakfast

9:00 - 9:50
Lecture 2: Learning factored transition models for planning in complex hybrid spaces
Leslie Kaelbling

9:50 - 10:40
Lecture 2
Josh Tenenbaum

10:40 - 11:20
Coffee Break

11:20 - 12:10
Lecture 2: Meta-learning
Joaquin Vanschoren

12:10 - 13:00
Lecture 2: Conditional GANs and Data Prediction
Phillip Isola

13:00 - 15:00
Lunch

15:00 - 15:50
Lecture 3: Integrating Domain-Knowledge into Deep Learning
Ruslan Salakhutdinov

15:50 - 16:40
Lecture 1: The Principle of Least Cognitive Action
Marco Gori

16:40 - 17:20
Coffee Break

17:20 - 18:10
Lecture 2: Model-based reinforcement learning II
Ioannis Antonoglou

18:10 - 19:00
Lecture 3: AlphaZero: A general model-based planning reinforcement learning algorithm for board games
Ioannis Antonoglou

19:30 - 21:30
Dinner

7:30 - 9:00
Breakfast

9:00 - 9:50
Lecture 3
Josh Tenenbaum

9:50 - 10:40
Lecture 3: Learning to speed up planning in complex hybrid spaces
Leslie Kaelbling

10:40 - 11:20
Coffee Break

11:20 - 12:10
Lecture 2: Quasi-Periodic Temporal Environments
Marco Gori

12:10 - 13:00
Lecture 3: AutoML and meta-learning for neural networks
Joaquin Vanschoren

13:00 - 15:00
Lunch

15:00 - 15:50
Lecture 1: Latest advances in enhancing Interpretability in Data Science via means of Mathematical Optimization (Part 1)
Dolores Romero Morales

15:50 - 16:40
Lecture 3: GANs for Domain Translation
Phillip Isola

16:40 - 17:20
Coffee Break

17:20 - 18:10
Building Iride: how to mix deep learning and Ontologies techiniques to understand language
Raniero Romagnoli

18:10 - 19:00
Flash-talk: tell me about yourself in five minutes
Vincenzo Sciacca

19:30 - 21:30
Dinner

7:30 - 9:00
Breakfast

9:00 - 9:50
Lecture 1: The Information Theory of Deep Learning: Towards Interpretable Deep Neural Networks - Rethinking Computational Learning theory
Naftali Tishby

9:50 - 10:40
Lecture 1: Advanced topics: Graph Neural Networks
Oriol Vinyals

10:40 - 11:20
Coffee Break

11:20 - 12:10
Lecture 1: KNIME training session 1
Giuseppe Di Fatta

12:10 - 13:00
Lecture 2: The Information Theory of Deep Learning: Towards Interpretable Deep Neural Networks - The role Stochastic Gradient Descent in achieving the Information Bottleneck optimal bound
Naftali Tishby

13:00 - 15:00
Lunch

15:00 - 15:50
Lecture 2: Latest advances in enhancing Interpretability in Data Science via means of Mathematical Optimization (Part 2)
Dolores Romero Morales

15:50 - 16:40
Lecture 3: Developmental Visual Agents
Marco Gori

16:40 - 17:20
Coffee Break

17:20 - 18:10
Lecture 2: KNIME training session 2
Giuseppe Di Fatta

18:10 - 19:00
Lecture 3: Data-intensive Knowledge Discovery from Brain Imaging of Alzheimer’s Disease Patients
Giuseppe Di Fatta

19:30 - 21:30
Dinner

7:30 - 9:00
Breakfast

9:00 - 9:50
Lecture 2: Reinforcement and Imitation Learning at Scale: AlphaStar and Beyond
Oriol Vinyals

9:50 - 10:40
Lecture 3: The Information Theory of Deep Learning: Towards Interpretable Deep Neural Networks - The computational benefits of the hidden layers and the role of symmetry for the interpretability of the layers
Naftali Tishby

10:40 - 11:20
Coffee Break

11:20 - 12:10
Lecture 3: Representation Learning With Generative Models
Oriol Vinyals

12:10 - 13:00
Lecture 3: Latest advances in enhancing Interpretability in Data Science via means of Mathematical Optimization (part 3)
Dolores Romero Morales

13:00 - 15:00
Lunch

15:00 - 21:30
Social Tour of Siena & Dinner in Contrada

Departure: July 20, 2019

ACDL-2019-Programme PDF Version