Intel AI at NeurIPS 2019

December 8 - 14, 2019 in Vancouver, B.C.

Intel is a top sponsor of the 33rd annual Conference on Neural Information Processing Systems (NeurIPS). Each year, thousands of leading academics and researchers converge to exchange research on neural information processing systems in biological, technological, mathematical and theoretical aspects. Stop by Intel AI’s booth to discover our complete AI hardware portfolio, backed by “write once, deploy anywhere” software and groundbreaking research.

NeurIPS 2019 Expo Day: Sunday, December 8th

NeurIPS Expo is a one day event taking place Dec. 8, 2019 prior to the NeurIPS conference to give sponsors a forum to showcase technologies, make announcements, or hold a press conference. Intel AI will be presenting the following talks and demos on Expo Day. Stop by the Intel AI booth #507 in the east exhibition hall afterward.

Exposition Hall: Monday December 9th – Wednesday, December 11th

Visit the Intel booth #507 and learn how Intel AI is breaking new ground in AI research. Join us for in-booth theater presentations, demonstrations, and the opportunity to connect with fellow researchers.

Agenda


Expo Day - Day 1

Sunday December 8, 2019

Title Time Location Abstract
Intel® Nervana™ NNP: Domain-Specific Architectures for Inference & Training 9:10am - 9:30am Vancouver Convention Center TALK: This talk will cover how we designed flexibility without sacrificing performance with the Intel Nervana NNP for Inference (NNP-I), scalability with the NNP for Training (NNP-T) for the most complex models, and software stacks to enable programmability through standard frameworks.
Efficient Deep Learning computing with Intel® Nervana™ Neural Network Processor for Training 9:00am - 5:30pm Vancouver Convention Center DEMO: The NNP-T is designed to maximize efficiency in power usage, memory and communication by increasing compute utilization for AI training needs instead of just peak TOPS. We will demonstrate end-to-end training of an image classification workload, ResNet50, using a popular deep learning framework.

Accepted Paper Presentations - Day 3

Tuesday December 10, 2019

Title Time Location Authors Abstract
Deep Equilibrium Models - SPOTLIGHT PAPER 10:40am - 12:45pm Vancouver Convention Center Shaojie Bai – Carnegie Mellon University, J. Zico Kolter – Carnegie Mellon University, Vladlen Koltun – Intel Intelligent Systems Lab

Oral Presentation:
West Ballroom C (10:40am – 10:45am)
Poster Session:
East Exhibition Hall B&C Poster #137 (10:45 am – 12:45 pm)

View paper ›

Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks 10:45am - 12:45pm East Exhibition Hall B&C Poster #15 Yiwen Guo – Intel Labs China, Ziang Yan – Tsinghua University, Changshui Zhang – Tsinghua University View paper ›
Differentiable Cloth Simulation for Inverse Problems 10:45am - 12:45pm East Exhibition Hall B&C Poster #138 Junbang Liang – University of Maryland, Computer Science, Ming Lin – University of Maryland, Computer Science, Vladlen Koltun – Intel Intelligent Systems Lab View paper ›
DATA: Differentiable ArchiTecture Approximation 5:30pm - 7:30pm East Exhibition Hall B&C Poster #2 Jianlong Chang – National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Xinbang Zhang – Institute of Automation, Chinese Academy of Science, Yiwen Guo – Intel Labs China, Gaofeng Meng – Institute of Automation, Chinese Academy of Sciences, Shiming Xiang – Chinese Academy of Sciences, China, Chunhong Pan – Institute of Automation, Chinese Academy of Sciences View paper ›
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model 5:30pm - 7:30pm East Exhibition Hall B&C Poster #155 Atilim Gunes Baydin – University of Oxford, Lei Shao – Intel Corporation, Wahid Bhimji – Berkeley lab, Lukas Heinrich – New York University Saeid Naderiparizi – University of British Columbia, Andreas Munk – University of British Columbia, Jialin Liu – Lawrence Berkeley National Lab, Bradley Gram-Hansen – University of Oxford, Gilles Louppe – University of Liège, Lawrence Meadows – Intel Corporation, Philip Torr – University of Oxford, Victor Lee – Intel Corporation, Kyle Cranmer – New York University, Mr. Prabhat – LBL/NERSC, Frank Wood – University of British Columbia View paper ›

Accepted Paper Presentations - Day 4

Wednesday December 11, 2019

Title Time Location Authors Abstract
Modeling Uncertainty by Learning A Hierarchy of Deep Neural Connections 10:45am - 12:45pm East Exhibition Hall B&C Poster #45

Yaniv Gurwic – Intel AI Lab, Shami Nisimov – Intel AI Lab, Gal Novik – Intel AI Lab, Raanan Rohekar – Intel AI Lab

View paper ›

Learn more ›

Post training 4-bit quantization of convolutional networks for rapid-deployment 10:45am - 12:45pm East Exhibition Hall B&C Poster #105 Ron Banner – Intel AI Lab, Yury Nahshan – Intel AI Lab, Daniel Soudry – Technion Learn more ›
Untangling in Invariant Speech Recognition 5:00pm - 7:00pm East Exhibition Hall B&C Poster #241 Cory Stephenson – Intel AI Lab, Suchismita Padhy – Intel AI Lab, Hanlin Tang – Intel AI Lab, Oguz Elibol – Intel AI Lab, Jenelle Feather – MIT, Josh McDermott – MIT, SueYeon Chung – MIT Learn more ›

Accepted Paper Presentations - Day 5

Thursday December 12, 2019

Title Time Location Authors Abstract
Generalization In Multitask Deep Neural Classifiers A Statistical Physics Approach 10:45am - 12:45pm East Exhibition Hall B&C Poster #55 Tyler Lee – Intel AI Lab, Anthony Ndirango – Intel AI Lab View paper ›
Goal-conditioned Imitation Learning 10:45am - 12:45pm East Exhibition Hall B&C Poster #229 Yiming Ding – University of California, Berkeley, Carlos Florensa – UC Berkeley, Pieter Abbeel – UC Berkeley, Mariano Phielipp – Intel AI Lab View paper ›
A Zero-Positive Learning Approach for Diagnosing Software Performance Regression 5:00pm - 7:00pm East Exhibition Hall B&C Poster #120 Mejbah Alam – Intel Labs, Justin Gottschlich – Intel Labs, Nesime Tatbul – Intel Labs, Javier Turek – Intel Labs, Timothy Mattson – Intel Labs, Abdullah Muzahid – Intel Labs Learn more ›

Workshops Accepted Paper Presentations - Day 2

Monday December 9, 2019

Title Time Location Authors Abstract
Layout Composition from Attributed Scene Graphs 8:00am - 6:00pm Women In Machine Learning (WiML) Subarna Tripathi – Intel AI Lab, Anahita Bhiwandiwalla – Intel AI Lab Paper ›
Triplet-Aware Scene Graph Embeddings 8:00am - 6:00pm
Women In Machine Learning (WiML) Brigit Schroeder – Intel AI Lab, Subarna Tripathi – Intel AI Lab, Hanlin Tang – Intel AI Lab Paper ›
A Comparison Of Loss Weighting Strategies For Multitask Learning In Deep Neural Networks 8:00am - 6:00pm Women In Machine Learning (WiML)
Ting Gong – Intel AI Lab, Suchismita Padhy – Intel AI Lab, Tyler Lee – Intel AI Lab, Cory Stephenson – Intel AI Lab, Oguz Elibol – Intel AI Lab Paper ›
Multimodal Understanding of Passenger Intents in Autonomous Vehicles 8:00am - 6:00pm
Women In Machine Learning (WiML) Eda Okur – Intel Labs, Shachi H. Kumar – Intel Labs, Saurav Sahay – Intel Labs, Lama Nachman – Intel Labs Paper ›
Neural Network Autoencoders for Compressed Neuroevolution 7:00am - 8:00pm LatinX in AI Somdeb Majumdar – Intel AI Lab, Santiago Miret – Intel AI Lab  

Workshops Accepted Paper Presentations - Day 6

Friday December 13, 2019

Title Time Location Authors Abstract
Q8BERT, A 8Bit Quantized BERT 8:00am - 6:40pm EMC2: Energy Efficient Machine Learning and Cognitive Computing Ofir Zafrir – Intel AI Lab, Guy Boudoukh – Intel AI Lab, Peter Izsak – Intel AI Lab, Moshe Wasserblat – Intel AI Lab

Read the blog here ›

Paper ›

Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models 8:00am - 6:40pm EMC2: Energy Efficient Machine Learning and Cognitive Computing Peter Izsak – Intel AI Lab, Shira Guskin – Intel AI Lab, Moshe Wasserblat – Intel AI Lab Paper ›
Improving MFVI in Bayesian Neural Networks with Empirical Bayes: a Study with Diabetic Retinopathy Diagnosis 8:00am - 6:45pm Bayesian Deep Learning Workshop Ranganath Krishnan – Intel Labs, Mahesh Subedar – Intel Labs, Omesh Tickoo – Intel Labs, Angelos Filos – Univ. of Oxford, Yarin Gal – Univ. of Oxford Paper ›
Deep Probabilistic Models to Detect Data Poisoning Attacks 8:00am - 6:45pm Bayesian Deep Learning Workshop Mahesh Subedar – Intel Labs, Nilesh Ahuja – Intel Labs, Ranganath Krishnan – Intel Labs, Ibrahima Ndiour – Intel Labs, Omesh Tickoo – Intel Labs Paper ›
Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection 8:00am - 6:45pm Bayesian Deep Learning Workshop Nilesh Ahuja – Intel Labs, Ibrahima Ndiour – Intel Labs, Trushant Kalyanpur, Omesh Tickoo – Intel Labs Paper ›
Leveraging Topics and Audio Features with Multimodal Attention for Audio Visual Scene-Aware Dialog 8:30am - 6:30pm Visually Grounded Interaction and Language Workshop Shachi H. Kumar – Intel Labs, Eda Okur – Intel Labs, Saurav Sahay – Intel Labs, Jonathan Huang – Intel Labs, Lama Nachman – Intel Labs Paper ›
LISA: Towards Learned DNA Sequence Search 8:00am - 6:00pm Workshop on Systems for Machine Learning Darryl Ho – MIT, Jialin Ding – MIT, Sanchit Misra – MIT, Nesime Tatbul – Intel Labs, Vikram Nathan – MIT, Vasimuddin Md – Intel Labs, Tim Kraska – MIT

This paper has been selected for an oral presentation.

Paper ›

Real-time Approximate Inference for Scene Understanding with Generative Models 8:00am - 6:00pm Perception as Generative Reasoning Workshop Javier Felip Leon – Intel Labs, Nilesh Ahuja – Intel Labs, David Gomez-Gutierrez – Intel Labs, Omesh Tickoo – Intel Labs, Vikash Mansinghka – MIT Paper ›

Workshops Accepted Paper Presentations - Day 7

Saturday December 14, 2019

Title Time Location Authors Abstract
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination 8:00am - 7:00pm Deep Reinforcement Learning Workshop Shauharda Khadka – Intel AI Lab, Somdeb Majumdar – Intel AI Lab, Santiago Miret – Intel AI Lab, Stephen McAleer – Intel AI Lab, Kagan Tumer – Oregon State University Paper ›
SEERL: Sample Efficient Ensemble Reinforcement Learning 8:00am - 7:00pm Deep Reinforcement Learning Workshop Rohan Saphal – Indian Institute of Technology Madras, Balaraman Ravindran – Indian Institute of Technology, Madras, Dheevatsa Mudigere – Facebook, Sasikanth Avancha, Bharat Kaul – Intel Labs  
Multi-Context Term Embeddings: the Use Case of Corpus-based Term Set Expansion 8:00am - 6:00pm Context and Compositionality in Biological and Artificial Neural Systems Workshop Jonathan Mamou – Intel AI Lab, Oren Pereg – Intel AI Lab, Moshe Wasserblat – Intel AI Lab, Ido Dagan – Bar Ilan University, Israel Paper ›
Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder 8:00am - 6:30pm Machine Learning and the Physical Sciences (ML4PS) Workshop Kara Lamb – Cooperative Institute for Research in the Environmental Sciences, Garima Malhotra – University of Michigan, Athanasios Vlontzos – Imperial College London, Edward Wagstaff – University of Oxford, Atılım Günes Baydin – University of Oxford, Anahita Bhiwandiwalla – Intel AI Lab, Yarin Gal – University of Oxford, Alfredo Kalaitzis – Element AI, Anthony Reina – Intel AIPG, Asti Bhatt – SRI International Paper ›
Learning to Vectorize using Deep Reinforcement Learning 8:00am - 6:00pm ML for Systems Workshop Ameer Haj-Ali, Nesreen Ahmed – Intel Labs, Ted Willke – Intel Labs, Sophia Shao, Krste Asanovic, Ion Stoica  
A Weak Supervision Approach to Detecting Visual Anomalies for Automated Testing of Graphics Units 11:00am - 11:15am ML for Systems Workshop Tom Hope, Data-Science Team Lead – Intel IT Advanced Analytics, Adi Szeskin, Data Scientis) – Intel IT Advanced Analytics, Dr. Itay Lieder, Data Scientist – Intel IT Advanced Analytics, Dr. Lev Faivishevsky, Data Scientist – Intel IT Advanced Analytics, and Dr. Amitai Armon, Chief Data Scientist & Principal Engineer – Intel IT Advanced Analytics

Oral Presentation

Paper ›

Workshop on Robot Learning 9:00am - 6:00pm Workshop on Robot Learning Siyu Zhou, Mariano Phielipp, Jorge Sefair, Sara Walker, Heni Ben Amor Paper ›
Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration 9:00am - 6:00pm Workshop on Robot Learning Simon Stepputtis – Arizona State University, Joseph Campbell, Mariano Phielipp – Intel AI Lab, Chitta Baral – Arizona State University, Heni Ben Amor – Arizona State University Paper ›

Event Authors


Careers


If you are interested in discovering AI careers that reshape business and society, be sure and stop by our booth and meet our recruiting team or visit the Intel AI careers page where you can explore different roles and join our talent network.

Follow us @IntelAI and @IntelAIResearch for more updates from @NeurIPS and the Intel AI research team!@NeurIPSConf