Principled Approaches to Deep Learning
Andrzej Pronobis · Robert Gens · Sham Kakade · Pedro Domingos

Thu Aug 10th 08:30 AM -- 05:30 PM @ C4.5
Event URL: »

The recent advancements in deep learning have revolutionized the field of machine learning, enabling unparalleled performance and many new real-world applications. Yet, the developments that led to this success have often been driven by empirical studies, and little is known about the theory behind some of the most successful approaches. While theoretically well-founded deep learning architectures had been proposed in the past, they came at a price of increased complexity and reduced tractability. Recently, we have witnessed considerable interest in principled deep learning. This led to a better theoretical understanding of existing architectures as well as development of more mature deep models with solid theoretical foundations. In this workshop, we intend to review the state of those developments and provide a platform for the exchange of ideas between the theoreticians and the practitioners of the growing deep learning community. Through a series of invited talks by the experts in the field, contributed presentations, and an interactive panel discussion, the workshop will cover recent theoretical developments, provide an overview of promising and mature architectures, highlight their challenges and unique benefits, and present the most exciting recent results.

08:30 AM Welcome and Opening Remarks (Talk)
08:45 AM Invited Talk 1 - Sanjeev Arora (Talk)
09:15 AM Contributed Presentation 1 - Towards a Deeper Understanding of Training Quantized Neural Networks (Talk)
09:30 AM Invited Talk 2 - Surya Ganguli (Talk)
10:00 AM Coffee Break and Poster Session (Break)
10:45 AM Invited Talk 3 - Ruslan Salakhutdinov (Talk)
11:15 AM Invited Talk 4 - Pedro Domingos (Talk)
11:45 AM Contributed Presentation 2 - LibSPN: A Library for Learning and Inference with Sum-Product Networks and TensorFlow (Talk)
12:00 PM Lunch (Break)
01:30 PM Invited Talk 5 - Tomaso Poggio (Talk)
02:00 PM Contributed Presentation 3 - Emergence of invariance and disentangling in deep representations (Talk)
02:15 PM Invited Talk 6 - Nathan Srebro (Talk)
02:45 PM Contributed Presentation 4 - The Shattered Gradients Problem: If resnets are the answer, then what is the question? (Talk)
03:00 PM Coffee Break 2 and Poster Session (Break)
03:45 PM Contributed Presentation 5 - Towards Deep Learning Models Resistant to Adversarial Attacks (Talk)
04:00 PM Panel Discussion <span> <a href="#"></a> </span>
05:20 PM Closing Remarks and Awards (Talk)

Author Information

Andrzej Pronobis (University of Washington)

Andrzej Pronobis is a Research Associate in the Department of Computer Science and Engineering at the University of Washington in Seattle, as well as a Senior Researcher at KTH Royal Institute of Technology in Stockholm, Sweden. His research is at the intersection of robotics, deep learning and computer vision, with focus on perception and spatial understanding mechanisms for mobile robots and their role in the interaction between robots and human environments. His recent interests include application of tractable probabilistic deep models to planning and learning semantic spatial representations. He is a recipient of a prestigious Swedish Research Council Grant for Junior Researchers and a finalist for the Georges Giralt Ph.D. award for the best European Ph.D. thesis in robotics.

Robert Gens (Google)
Sham Kakade (University of Washington)
Pedro Domingos (University of Washington)

More from the Same Authors