Deep Learning in Autonomous Driving and Drug Design
Sprache des Vortragstitels:
Englisch
Original Tagungtitel:
The 5th KAST-Leopoldina Bilateral Symposium on ?AI and Machine Learning: Technology, Perspective and Applications?
Sprache des Tagungstitel:
Englisch
Original Kurzfassung:
Deep Learning has emerged as one of the most successful fields of machine learning and artificial intelligence with overwhelming success in industrial speech, language and vision benchmarks. Consequently it became the central field of research for IT giants like Google, facebook, Microsoft, Baidu, and Amazon. Deep Learning is founded on novel neural network techniques, the recent availability of very fast computers, and massive data sets. In its core, Deep Learning discovers multiple levels of abstract representations of the input.
I invented LSTM recurrent neural networks which currently exhibit overwhelmingly successes in different AI fields like speech, language, and text analysis. Since 2012 LSTM is used in Google?s Android speech recognizer, since 2015 in Google Voice transcription, since 2016 in Google?s Allo , since 2016 in Apple?s iOS 10 ?QuickType? , and since 2016 in Google?s Translate. Based on our expertise in LSTM networks, we use LSTM for natural language processing (NLP ? a typical field of AI) in collaboration with companies like Zalando and Bayer, e.g. to analyze fashion blogs or twitter news related to health. In the AUDI Deep Learning Center, which I am heading, and in the collaboration with NVIDIA we apply Deep Learning to advance autonomous driving. In particular we use LSTMs for sequence prediction and for attention to analyze traffic scenes to make driving decisions faster than previous systems. With Deep Learning we won the NIH Tox21 challenge and identified unknown side effects of drug candidates based on data from bioassays and high content imaging. We deploy Deep Neural Networks to toxicity and target prediction in collaboration with pharma companies like Janssen, Merck, Novartis, AstraZeneca, GSK, Bayer together with hardware-related companies like Intel, HP, NVIDIA and others.