MACHINE LEARNING Games and Beyond. Calvin Lin, NVIDIA

Similar documents
THE NEXT WAVE OF COMPUTING. September 2017

23270: AUGMENTED REALITY FOR NAVIGATION AND INFORMATIONAL ADAS. Sergii Bykov Technical Lead Machine Learning 12 Oct 2017

SUPERCHARGED COMPUTING FOR THE DA VINCIS AND EINSTEINS OF OUR TIME

Deep learning for INTELLIGENT machines

Using Hybrid Reality to Explore Scientific Exploration Scenarios

KÜNSTLICHE INTELLIGENZ JOBKILLER VON MORGEN?

Applying Virtual Reality, and Augmented Reality to the Lifecycle Phases of Complex Products

GPU ACCELERATED DEEP LEARNING WITH CUDNN

Vision with Precision Webinar Series Augmented & Virtual Reality Aaron Behman, Xilinx Mark Beccue, Tractica. Copyright 2016 Xilinx

LOOKING AHEAD: UE4 VR Roadmap. Nick Whiting Technical Director VR / AR

Harnessing the Power of AI: An Easy Start with Lattice s sensai

NVIDIA APEX: From Mirror s Edge to Pervasive Cinematic Destruction. Anders Caspersson, DICE Monier Maher, NVIDIA Jean Pierre Bordes, NVIDIA

From Cloud Computing To Online Gaming. Mark Sung General Manager zillians.com

Challenges in Transition

DEEP LEARNING ON RF DATA. Adam Thompson Senior Solutions Architect March 29, 2018

Presenter s biographies

NVIDIA APEX: High-Definition Physics with Clothing and Vegetation. Michael Sechrest, IDV Monier Maher, NVIDIA Jean Pierre Bordes, NVIDIA

AI Application Processing Requirements

HPC + AI. Mike Houston

DEMIGOD DEMIGOD. characterize stalls and pop-ups during game play. Serious gamers play games at their maximum settings driving HD monitors.

Ben Baker. Sponsored by:

Image Processing Architectures (and their future requirements)

Document downloaded from:

Embedding Artificial Intelligence into Our Lives

Neural Networks The New Moore s Law

GPU-accelerated SDR Implementation of Multi-User Detector for Satellite Return Links

Satellite Identification Imaging for Small Satellites Using NVIDIA

VSI Labs The Build Up of Automated Driving

The Power of Exponential Thinking

Computational Efficiency of the GF and the RMF Transforms for Quaternary Logic Functions on CPUs and GPUs

VR Best Practices: Putting the Fun in VR Funhouse. Amanda Bott - March 3, 2017

Exploring Virtual Reality (VR) with ArcGIS. Euan Cameron Simon Haegler Mark Baird

ADAS Development using Advanced Real-Time All-in-the-Loop Simulators. Roberto De Vecchi VI-grade Enrico Busto - AddFor

Poker AI: Equilibrium, Online Resolving, Deep Learning and Reinforcement Learning

CUDA-Accelerated Satellite Communication Demodulation

VR-OOS System Architecture Workshop zu interaktiven VR-Technologien für On-Orbit Servicing

SPIDERMAN VR. Adam Elgressy and Dmitry Vlasenko

Multiband NFC for High-Throughput Wireless Computer Vision Sensor Network

Revolutionize the Service Industries with AI 2016 Service Robot

Haptic Rendering of Large-Scale VEs

Deep Learning Overview

Transformation to Artificial Intelligence with MATLAB Roy Lurie, PhD Vice President of Engineering MATLAB Products

ADAS COMPUTER VISION AND AUGMENTED REALITY SOLUTION

5G R&D at Huawei: An Insider Look

More Efficient and Intuitive PLM by Integrated AR/VR. Round Table Session Georg Fiechtner

Construction of visualization system for scientific experiments

DEEP LEARNING A NEW COMPUTING MODEL. Sundara R Nagalingam Head Deep Learning Practice

Creating Intelligence at the Edge

Table of Contents HOL EMT

A.I in Automotive? Why and When.

2015 The MathWorks, Inc. 1

SCAI SuperComputing Application & Innovation. Sanzio Bassini October 2017

Global Cloud Network Evolution

REVOLUTIONIZING THE COMPUTING LANDSCAPE AND BEYOND.

Great Minds. Internship Program IBM Research - China

Artificial intelligence, made simple. Written by: Dale Benton Produced by: Danielle Harris

Introduction. Video Game Design and Development Spring part of slides courtesy of Andy Nealen. Game Development - Spring

Creating the Right Environment for Machine Learning Codesign. Cliff Young, Google AI

Visualizing the future of field service

Job Description. Commitment: Must be available to work full-time hours, M-F for weeks beginning Summer of 2018.

Virtual and Augmented Reality for Cabin Crew Training: Practical Applications

Table of Contents HOL ADV

Architectures For Intelligence The 22nd Carnegie Mellon Symposium On Cognition Carnegie Mellon Symposia On Cognition Series

2018 Avanade Inc. All Rights Reserved.

Introduction. Video Game Programming Spring Video Game Programming - A. Sharf 1. Nintendo

Physics Based Sensor simulation

Machine Learning and Decision Making for Sustainability

Asia Conference Singapore

CS6700: The Emergence of Intelligent Machines. Prof. Carla Gomes Prof. Bart Selman Cornell University

A Winning Combination

Modeling and Simulation: Linking Entertainment & Defense

Development and Integration of Artificial Intelligence Technologies for Innovation Acceleration

Artificial Intelligence Machine learning and Deep Learning: Trends and Tools. Dr. Shaona

Virtual Reality Mobile 360 Nanodegree Syllabus (nd106)

EMPOWERING THE CONNECTED FIELD FORCE WORKER WITH ADVANCED ANALYTICS MATTHEW SHORT ACCENTURE LABS

Data-Starved Artificial Intelligence

Disrupting our way to a Very Human City

Propietary Engine VS Commercial engine. by Zalo

Overview of current developments in haptic APIs

Prototyping Vision-Based Classifiers in Constrained Environments

MANPADS VIRTUAL REALITY SIMULATOR

Image Processing Architectures (and their future requirements)

Sensible Chuckle SuperTuxKart Concrete Architecture Report

Combining ROS and AI for fail-operational automated driving

GESTURE RECOGNITION FOR ROBOTIC CONTROL USING DEEP LEARNING

Introduction to Game Design. Truong Tuan Anh CSE-HCMUT

Learning Media Based on Augmented Reality Applied on the Lesson of Electrical Network Protection System

Developing a GPU Processing Framework for Accelerating Remote Sensing Algorithms

VIRTUAL REALITY LAB Research group Softwarevisualisation in 3D and VR

Architecting Systems of the Future, page 1

AI Frontiers. Dr. Dario Gil Vice President IBM Research

Image-Domain Gridding on Accelerators

Technology Transfers Opportunities, Process and Risk Mitigation. Radhika Srinivasan, Ph.D. IBM

VR/AR with ArcGIS. Pascal Mueller, Rex Hansen, Eric Wittner & Adrien Meriaux

Industrial Keynotes. 06/09/2018 Juan-Les-Pins

DESIGN STYLE FOR BUILDING INTERIOR 3D OBJECTS USING MARKER BASED AUGMENTED REALITY

Programme TOC. CONNECT Platform CONNECTION Client MicroStation CONNECT Edition i-models what is comming

March, Global Video Games Industry Strategies, Trends & Opportunities. digital.vector. Animation, VFX & Games Market Research

Appendix A ACE exam objectives map

Transcription:

MACHINE LEARNING Games and Beyond Calvin Lin, NVIDIA

THE MACHINE LEARNING ERA IS HERE And it is transforming every industry... including Game Development

OVERVIEW NVIDIA Volta: An Architecture for Machine Learning NVIDIA GameWorks Materials & Textures Project Isaac & Holodeck

NVIDIA VOLTA An Architecture for Machine Learning

NVIDIA VOLTA GPU: KEY FEATURES Tensor Cores for deep learning 2 nd generation NVIDIA NVLink HBM2 memory Cooperative groups Volta-optimized software

TENSOR CORES An Exponential Leap in Performance Equipped with 640 Tensor Cores 120T Tensor FLOPS Over a 5X over NVIDIA Pascal architecture.

TESLA V100 VS. TESLA P100

2 ND GEN NVLINK Scalability for Rapid Time-to-Solution High-speed interconnect technology 2X throughput over previous gen Enable large scale parallel computing

HBM2 MEMORY Faster, Higher Efficiency 16GB HBM2 memory 900 GB/sec peak bandwidth

COOPERATIVE GROUPS New programming model in CUDA 9 Independent thread scheduling New way for organizing groups of communicating threads

VOLTA-OPTIMIZED SOFTWARE GPU-Accelerated Frameworks and Applications NVIDIA Deep Learning SDK libraries: cudnn, cublas, NCCL, TensorRT

NVIDIA GameWorks Materials & Textures Game Content Creation by Machine Learning

What is Machine Learning to Game Development? Content Creation Better game assets with less effort Game AI Bots are smarter and more fun User Interface Innovative ways to interact Super-Resolution Material from Photos Texture Multiplier Physically Based Animation Speech Synthesis Human-like AI Player

NVIDIA s Goal for Game Content Creation Accelerate content creation Remove the mundane/repetitive Increase asset quality/realism Promote creativity

GameWorks: Materials & Textures Set of tools targeting the game industry using machine learning Tools in the initial release: Photo To Material: 2shot Super-resolution Texture Multiplier GameWorks Materials & Textures beta https://gwmt.nvidia.com

Photo to Material: 2Shot Using CNN to generate PBR materials Two input photos: Flash image (with flash) Guide image (without flash) Diffuse albedo Flash image Specular Normals Glossiness Anisotropy Guide image

Photo to Material: 2Shot Using CNN to generate PBR materials Two input photos: Flash image (with flash) Guide image (without flash) vs. 2Shot Traditional

Texture Multiplier Example texture in, new textures out Limitless images generated

Given low-resolution image Super-Resolution Amplify the image by 2x or 4x using deep learning method Far better quality than image filtering H W Upscale Constructed high-resolution image n * H n * W* W

Super-Resolution Convolutional Auto-Encoder Convolutional operators HR image LR image Mapping Mapping in the feature space Mapping

http://gwmt.nvidia.com

Project Isaac & Holodeck Machine Learning Beyond Games

PROJECT ISAAC Virtual Simulator for Robots

Hockey Demo Training: real world vs. virtual world https://www.nvidia.com/en-us/deeplearning-ai/industries/robotics/

ISAAC Training robots in the virtual world, downloading to the real world The faster, safer, cheaper way to train robots Faster rapid domain adaptation Safer train scenarios difficult to do in real world Cheaper cost saving regression test and labelling

The Robotic Simulator 1. The processor of NVIDIA Jetson TX 2. The software stack for perceive, localize, plan and take action 3. Isaac Lab a real world simulator 4. A collection of reference platforms like drones and submersibles

Isaac Lab Training in the virtual world DNN / Compute platform OpenAI Gym Ease transition from training to inference Rendering Customized UE4 Camera, lidar, radar sensing and segmentation Physical Simulation PhysX Hardware-accelerated simulation in the cloud

Jetson Reference Platform Downloading to the real world Transfer training result to real world Quick iteration on tuning final products Open-sourced robotic platforms Various drones, submersibles, wheeled robots for developers to create & test prototypes

PROJECT HOLODECK

Koenigsegg Regera Demo Holodeck makes it easy to import render enormous models. The Koenigsegg Regera supercar contains 50 million polygons. http://www.nvidia.com/object/nvidiaproject-holodeck-notify-me.html

Holodeck Photorealistic, Collaborative VR Sight, sound and haptics Headset & gloves Models and physics Built on UE4 and utilizing GameWorks, VRWorks and DesignWorks Interaction and collaboration Machine learning for posture recognition

WRAP-UP: GAMES AND BEYOND

THANK YOU!