KIVI Innovation Drinks Twente An AI encounter with BrainCreators
Overview Short introduction BrainCreators ➢ Example use-cases ➢ AI maturity model ➢ The Application Gap ➢ Epilogue: pretty pictures ➢
BrainCreators applies 20+ years of experience in artificial intelligence to business challenges across all verticals Discover value Deploy solutions Accelerate teams Compile a strategic Implement scalable Inherit skills & best roadmap of viable solutions with maximum practices with business cases business impact expert coaching
TRUSTED BY
Use cases Smart Radio ➢ Logistics ➢ Fashion and Retail ➢ Steel quality control ➢ Genetics ➢ Telecommunication ➢
Smart Radio 24/7 news radio Smart Radio 10 hours original radio broadcast per day Automatically curated playlists of news content ● ● ● Additional podcast creation ● Taylored to a listener’s preferences Inconsistent manual tagging of content On demand ● ● ● Course segmentation of topics
Smart Radio AI under the hood Audio feature detection ● ● Detection of semantic overlap among existing labels Semi-supervised refinement of existing dataset ● ● Topic modeling Segment classification ●
Smart Radio Results (v1 in the making) Detect topics in segments ● ● Cut audio segments Provide relevant user content ●
Logistics Before application of AI Manual identification of address data for 15% of total volume ● ● 4% delivered to wrong address Geographical location of delivery points imprecise ● ● Delivery window too coarse
Logistics AI under the hood Fuzzy logic address matching ● GPS delivery point prediction ● ● Time window estimation & optimisation Automated location mapping (inc. po-boxes) ● ● Trained on historic data and self learning
Logistics Results Manual correction reduced to <2% of total volume ● ● Delivery failures reduced by 50% 2000 man hours saved per month ● ● Improved customer service through better time windows
Fashion & retail Before Manual classification of products ● ● Complex mappings to market place taxonomies Poor quality of properties data ● ● Basic recommendations
Fashion & retail Under the hood Training set of 20+ Million products ● ● Combined Image & Text classifiers Sorting of products using complex features ● ● Human-in-the-loop data improvement
Fashion & retail Result Automated categorization >95% accurate ● ● Auto-enrichment of product data Product family recommendation ● ● Cross & upselling automation
Steel quality control General ● A major European steel producer ● Total of 7.1 million tonnes of steel products in 2016 ● High quality sheet and strip steel ● Automotive, packaging, and construction sectors
Steel quality control Initial Situation ● Kilometers of steel sheet each day ● Accurate quality assessment enables more profitable trading ● Defects need to be detected to prevent machine breaks ● Manual inspection supported by automatic camera system
Steel quality control Camera system ● Infrared cameras inspect moving steel sheets on conveyor belts ● Basic image processing detects regions of interest ● Manual inspection often needed ● Accuracy can still be improved
Steel quality control Data sets ● Up to 50 different defect types ● 5 million (!) new images each day ● Currently only 25 thousand annotated images available in total ● Severely imbalanced data sets ● Manual annotation is costly
Steel quality control Solution ● Deep Learning for robust image classification ● Ai & Active Learning approach for efficient image annotation ● Integration in existing systems ● Knowledge transfer to customer’s own tech team
Genetics for livestock the animal protein value chain
Genetics for livestock the animal protein value chain
Genetics for livestock Selective breeding ● Large scale selective breeding as an industrial optimization process Changing targets due to commercial, ● political, and environmental requirements Integration of different data sets, ● including genomics data Evaluation is either slow or imprecise ● Breeding value = Genetics + Environment
Genetics for livestock Challenge ● Predict carcass properties from measurements on live animals ● Numerical input data, e.g. weights at different ages ● Ultrascan visual data ● How can the ultrascans be used more effectively ?
Genetics for livestock Narrow passage ● Information can get lost in the narrow passage of human interpretation ● Deep learning helps to extract useful information from complex visual data ● Less requirements for human understanding of the images ● End-to-end learning combines visual Human understanding Deep Learning and non-visual data into one system
Fault detection in telecom Initial situation ● Very large telco network ● Hybrid Fibre Coax Up to 5M modems ● ● Modems report their status ● Thousands of relay points Diversity of legacy systems ● …..
Fault detection in telecom Challenge ● Manage fleet of field technicians ● Network errors and maintenance ● Detect & classify problems ● Find problem root causes ● Collect useful data
Fault detection in telecom Solution ● Dedicated data labeling software ● Network Anomaly Detection ● Generalize to all fault types ● AI Roadmap Human understanding Deep Learning
TRANSFORMING TO A DIGITAL ENTERPRISE
TRANSFORMING TO A DIGITAL ENTERPRISE Exploring
TRANSFORMING TO A DIGITAL ENTERPRISE Planning Exploring
TRANSFORMING TO A DIGITAL ENTERPRISE Experimenting Planning Exploring
TRANSFORMING TO A DIGITAL ENTERPRISE Productizing Experimenting Planning Exploring
TRANSFORMING TO A DIGITAL ENTERPRISE Scaling Productizing Experimenting Planning Exploring
TRANSFORMING TO A DIGITAL ENTERPRISE Data-Centric Scaling Productizing Experimenting Planning Exploring
The Application Gap
The Application Gap … between Research and Industry
The Application Gap … between Research and Industry Solved? .... really? ● When is something “solved” ? ● Has it been demonstrated to work once, under special circumstances? ● Or is it ready and safe to deploy in general, right now, for everyone ? ● Speech-to-text ? ● Self-driving cars ? ● … …
Andrew Ng: “AI is the new electricity” “ We have enough papers. Stop publishing, and start transforming people’s lives with technology! ”
The competitive landscape
Thank you! Maarten Stol maarten.stol@braincreators.com BrainCreators Prinsengracht 697 1017JV Amsterdam +31 (0)20 369 7260
Epilogue
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
BigGAN Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock, Jeff Donahue, Karen Simonyan
Recommend
More recommend
