No more seats available. We will record the talks and make the videos public after the workshop.
The workshop aims at bringing together leading scientists in deep learning and related areas within machine learning, artificial intelligence, mathematics, statistics, and neuroscience. No formal submission is required. Speakers are invited to present their recently published work as well as work in progress, and to share their vision and perspectives for the field.
Program
March 19th
- Kunihiko Fukushima (Fuzzy Logic Systems Institute): Artificial Vision by Deep CNN Neocognitron
- Moustapha Cisse (Facebook AI Research): Deep Learning in the Land of Adversity
- Gang Niu (The University of Tokyo and RIKEN-AIP): When Deep Learning Meets Weakly-Supervised Learning
- Babak Shahbaba (UC Irvine): Decoding of Hippocampal Neural Activity Using Deep Learning Methods Reveals Predictive Activation of Upcoming Sequence of Events
- Jun Zhu (Tsinghua University): ZhuSuan: A Probabilistic Programming Library for Bayesian Deep Learning
- Mohammad Emtiyaz Khan (RIKEN-AIP): Uncertainty through the Optimizer: Bayesian Deep Learning via Perturbed Adaptive Learning-Rate Methods
- Bob Williamson (Australian National University): Information Processing Equalities
- Klaus-Robert Mueller (TU Berlin): Machine Learning for the Sciences (tentative)
- Eunho Yang (KAIST): Reliable Predictions for Healthcare
March 20th
- Tom Schaul (DeepMind): Deep Reinforcement Learning
- Wee Sun Lee (National University of Singapore): Planning with Deep Neural Networks
- Naoaki Okazaki (Tokyo Institute of Technology): Generating Text with Deep Neural Networks
- Kevin Murphy (Google Research): Generative Models for Language and Vision
March 21st
- Shun-ichi Amari (RIKEN Brain Science Institute): Statistical Neurodynamics of Deep Networks
- Pradeep Ravikumar (Carnegie Mellon University): Destructive Deep Learning
- Sumio Watanabe (Tokyo Institute of Technology): Cross Validation and WAIC in Layered Neural Networks
- Le Song (Georgia Tech and Ant Financial): Enhancing Deep Learning with Structures
- Pierre Baldi (University of California, Irvine): Neural Network Complexity: Shallow versus Deep
- Taiji Suzuki (The University of Tokyo and RIKEN-AIP): Generalization Error and Compressibility of Deep Learning via Kernel Analysis
- Li Erran Li (Uber ATG and Columbia University): 3D Objection Detection: Recent Advances and Future Directions
- Amir Globerson (Tel Aviv University and Google): How SGD Can Succeed Despite Non-Convexity and Over-Specification
- Sho Sonoda (Waseda University): Transport Analysis of Denoising Autoencoder
- Yanghua Jin (Fudan University): Creating Anime Characters with GAN
March 22nd
- Tatsuya Harada (The University of Tokyo and RIKEN-AIP): Learning Deep Neural Networks from Limited Examples
- Jan Peters (TU Darmstadt & MPI-IS): Policy Search with the f-Divergence
- Masaaki Imaizumi (The Institute of Statistical Mathematics): Statistical Estimation for Non-Smooth Functions by Deep Neural Networks
- Jean-Philippe Vert (ENS Paris): Supervised Quantile Normalization
- Akiko Takeda (The Institute of Statistical Mathematics): Efficient DC Algorithm for Nonconvex Nonsmooth Optimization Problems
- James Kwok (Hong Kong University of Science and Technology): TBA
- Edgar Simo-Serra (Waseda University): Semi-Supervised Learning of Sketch Simplification
- Takayuki Osogami (IBM Research AI): Dynamic Determinantal Point Processes
- Masatoshi Hamanaka (RIKEN AIP): Music Structure Analysis based on Deep Learning
Venue
RIKEN Center for Advanced Intelligence Project (RIKEN-AIP),
located at Nihonbashi in the heart of Tokyo.
[Access]
Sponsors
Organizers
- Pierre Baldi (University of California, Irvine, USA)
- Masashi Sugiyama (RIKEN-AIP/University of Tokyo, Tokyo, Japan), Chair
- Kenji Fukumizu (Institute of Statistical Mathematics, Tokyo, Japan)
- Naonori Ueda (NTT/RIKEN-AIP, Tokyo, Japan)
Accommodation
There are plenty of hotels nearby. For example,
Better:
Average:
Economical:
Previous Editions
Previous editions of the workshop were held at