ICLR Expo Talk: Neurosymbolic Hybrid AI
Artificial intelligence and machine learning have experienced a renaissance in the past decade, thanks largely to the success of deep learning methods. However, while deep learning has proven itself to be extremely powerful, most of today’s most successful deep learning systems suffer from a number of important limitations, ranging from the requirement for enormous training data sets to lack of interpretability to vulnerability to “hacking”via adversarial examples. In my talk, I will survey some of these limitations and propose that one path forward involves building hybrid systems that combine neural networks with techniques and ideas from symbolic AI, a parallel tradition of AI whose origins date back to the beginning of AI. I will show example neurosymbolic hybrid systems where neural networks and symbolic systems complement each other’s strengths and weaknesses, enabling systems that are accurate, sample efficient, and interpretable. Finally, I will show other directions we are pursuing in the space of neuralsymbolic hybrid systems, and argue that these methods at the intersection provide a powerful path forward for the broad adoption of AI.
Speaker: Dr. David Cox, Director, MIT-IBM Watson AI Lab, IBM Research
Видео ICLR Expo Talk: Neurosymbolic Hybrid AI канала IBM Research
Speaker: Dr. David Cox, Director, MIT-IBM Watson AI Lab, IBM Research
Видео ICLR Expo Talk: Neurosymbolic Hybrid AI канала IBM Research
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
The IBM Quantum Summit Keynote with Darío Gil, Senior Vice President and Director of IBM ResearchYoshua Bengio: Symbolic AI in Contrast to Deep Learning (NeurIPS 2019)CNN: Convolutional Neural Networks Explained - ComputerphileWhat's Next in AI: Our VisionNeurosymbolic Programming - Yisong YueTop 5 things to know about neuro-symbolic AIHow to make AI hack-proof - 3 QuestionsMIT 6.S191 (2020): Neurosymbolic AINeurosymbolic AI ExplainedICLR 2020 | Yoshua Bengio, Yann LeCun Reflections (Self-Supervised Learning)Michio Kaku on the Evolution of Intelligence | Big ThinkMatt Botvinick - Holy Grail Questions at the Intersection of Neuroscience and AIArtificial Intelligence vs Machine Learning - Gary explainsA Brief History of Artificial IntelligenceSYNT 2020: Neuro-Symbolic Program Synthesis from Natural Language and DemonstrationsDiscovering Symbolic Models from Deep Learning with Inductive Biases (Paper Explained)How we teach computers to understand pictures | Fei Fei LiAI for Representation and Reasoning in Knowledge Bases of Science | Andrew McCallumOut of the AI Winter & Into the Neuro-Symbolic Future with Yoav Shoham