Brainchip Holdings Ltd. · ASX:BRN
Brainchip — Q3 2018 Earnings Presentation
27 slides from Brainchip's earnings presentation, Nov 2, 2018
Slide 1: BrainChip September 2018 Quarter Update
For personal use only BrainChip September 2018 Quarter Update Brainchip O C TO B E R 2017 | 1
Slide 2: Disclaimer
Disclaimer For personal use only This presentation is not a prospectus nor an offer for securities in any jurisdiction nor a securities recommendation. The information in this presentation is an overview and does not contain all information necessary for investment decisions. In making investment de
Slide 3: September 2018 Quarter Update
For personal use only September 2018 Quarter Update Announcement of AkidaTM Neuromorphic System-on-Chip (NSOC) Architecture Partnership with Telesikring to deliver AI-powered Video Analytics to Police and Security Customers across Scandinavia Acquistion of License to Cybersecurity technology from De
Slide 4: September 2018 Quarter Cash Receipts
For personal use only September 2018 Quarter Cash Receipts The Company finished the September 2018 quarter with a cash balance of US$9.995M. Cash receipts for the quarter were US$246,000. Headcount at the end of the quarter was 35 fulltime employees and two fulltime contractors in sales and marketin
Slide 5: December 2018 Quarter Outlook
For personal use only December 2018 Quarter Outlook The Company expects an increase in cash receipts from OEMs, System Integrators and other partners in the December quarter of 2018. The Company’s sales pipeline continues to grow and now includes over 500 leads, 105 active accounts, 55 qualified opp
Slide 6: BrainChip Application Update
For personal use only BrainChip Application Update Automotive Automobile Manufactures Third Party Vendors Civil Surveillance Original Equipment Manufacturers End-Users and System Integrators Gaming Neuromorphic computing for multiple markets Vision systems Cybersecurity Financial Technolog Agricultu
Slide 7: Akida Market Penetration
For personal use only Akida Market Penetration Company will provide investors insight with regard to activity in the following markets: Industrial – Internet-of-Things (IoT), Agricultural Technology, Financial Technology, Cybersecurity, Robotics, Process Control and Manufacturing Automation, , Surve
Slide 8: BrainChip and the AI Timeline
For personal use only BrainChip and the AI Timeline Brainchip O C TO B E R 2017 | 8
Slide 9: Semiconductor Industry Disruption
For personal use only Semiconductor Industry Disruption AI Acceleration Chipset Forecast 70,000 60,000 Training Inference General Purpose 50,000 40,000 $M 30,000 20,000 10,000 0 2018 2019 2020 2021 2022 2023 2024 2025 Brainchip Source: Tractica Deep Learning Chipsets, Q2 2018 O C TO B E R 2017 | 9
Slide 10: Neural Network Comparison
For personal use only Neural Network Comparison Convolutional Neural Networks Spiking Neural Networks Characteristic Result Characteristic Result Computational Matrix Multiplication, Math intensive, high Threshold logic, Math-light, low functions ReLU, Pooling, FC power, custom connection power, sta
Slide 11: Studio
For personal use only Studio Brainchip O C TO B E R 2017 | 11
Slide 12: BrainChip Studio Development History
For personal use only BrainChip Studio Development History Custom software deployments Gaming Civil surveillance Machine vision Mohegan Sun French Homeland Security (DGSI) SAFRAN augmented reality 10 years of development Las Vegas Trials French National Police (Paris, Toulouse) Real-time card and Fo
Slide 13: Challenges Facing Forensic Video Analysis
For personal use only Challenges Facing Forensic Video Analysis Exabytes of previously recorded video Low resolution and noisy environments Prohibitively expensive to “Classify” all video using deep learning Brainchip O C TO B E R 2017 | 13
Slide 14: BrainChip Studio Features and Benefits
For personal use only BrainChip Studio Features and Benefits Highly effective One-Shot learning to object Forensic Object rapidly search for recognition technology in Search patterns/suspects low-resolution environments Face Detection Automatic face Facial classification of and detection and top mat
Slide 15: Technology – BCS Learn
For personal use only Technology – BCS Learn BCS Learn It’s all about shape recognition, not biometrics and key points! BrainChip RECOGNIZE Recognition of patterns LEARN Visual target recognition with similar visual to identify model features Brainchip O C TO B E R 2017 | 15
Slide 16: BrainChip Accelerator Benefits
For personal use only BrainChip Accelerator Benefits BrainChip Accelerator FPS Increase Compared to Software Only 6x 6x 5x Improved probability of object detection Fast video scaling Faster time to results More channels, faster 3 Scales, 1 Model 3 Scales, 4 Models 6 Scales, 4 Models Lower total cost
Slide 17: For personal use only
For personal use only Brainchip O C TO B E R 2017 | 17
Slide 18: BrainChip Akida NSoC
For personal use only BrainChip AkidaTM NSoC World’s first Neuromorphic System on Chip (NSoC) Efficient neuron model Innovative training methodologies Everything required for embedded/edge applications On-chip processor Data->spike conversion Scalable for Server/Cloud Brainchip O C TO B E R 2017 | 1
Slide 19: Akida NSoC Architecture
For personal use only Akida NSoC Architecture Brainchip O C TO B E R 2017 | 19
Slide 20: Akida Neuron Fabric
Akida Neuron Fabric For personal use only Most efficient spiking neural Right-Sized for embedded network implementation 1.2M Neurons applications 10B Synapses 10 classifiers (CIFAR 10) Able to replicate most CNN 11 Layers functionality 517K Neurons Convolution Pooling 616M Synapses Fully connected M
Slide 21: Efficient Neuromorphic Computing Fabric
For personal use only Efficient Neuromorphic Computing Fabric Relative Implementation Efficiency Keys to efficiency (Neurons and Synapses) Fixed neuron model Right-sized Synapses minimized 300X on-chip RAM 6MB compared to 30-50MB Programmable training and firing thresholds Flexible neural processor
Slide 22: Neuromorphic Computing Benefits
For personal use only Neuromorphic Computing Benefits 83% Cifar-10 IBM ~$1,000 Cifar-10 TrueNorth Tremendous 82% ~$10 BrainChip throughput with low Top-1 Accuracy Akida 6K fps/w power 1.4K fps/w Math-lite, no MACs Cifar-10 No DRAM access 80% ~$1,000 79% Cifar-10 Intel ~$10 Xilinx ZC709 for weights M
Slide 23: Akida NSoC Applications
For personal use only Akida NSoC Applications Brainchip O C TO B E R 2017 | 23
Slide 24: Akida Development Environment
For personal use only Akida Development Environment Brainchip O C TO B E R 2017 | 24
Slide 25: Akida Introduction
For personal use only Akida Introduction World’s first NSoC Low power and footprint of neuromorphic computing Highest performance /w/$ Complete solution for embedded/edge applications – but scalable for cloud/server usage Sampling 2H 2019 Brainchip O C TO B E R 2017 | 25
Slide 26: Akida Architecture Press Coverage
For personal use only Akida Architecture Press Coverage EE Times (Rick Merritt) CiE Magazine (Amy Wallington) https:/https://www.eetimes.com/document.asp?doc_id=1333677/www.ee http://www.cieonline.co.uk/brainchip-announces-the-akida-architecture-a- times.com/document.asp?doc_id=1333677 neuromorphic-
Slide 27: Thank You
For personal use only Thank You Brainchip O C TO B E R 2017 | 27