Ian Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk)
Speaker: Ian Goodfellow
Abstract:
Until about 2013, most researchers studying machine learning for artificial intelligence all worked on a common goal: get machine learning to work for AI-scale tasks. Now that supervised learning works, there is a Cambrian explosion of new research directions: making machine learning secure, making machine learning private, getting machine learning to work for new tasks, reducing the dependence on large amounts of labeled data, and so on. In this talk I survey how adversarial techniques in machine learning are involved in several of these new research frontiers.
Presented at ICLR2019
Видео Ian Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk) канала Steven Van Vaerenbergh
Abstract:
Until about 2013, most researchers studying machine learning for artificial intelligence all worked on a common goal: get machine learning to work for AI-scale tasks. Now that supervised learning works, there is a Cambrian explosion of new research directions: making machine learning secure, making machine learning private, getting machine learning to work for new tasks, reducing the dependence on large amounts of labeled data, and so on. In this talk I survey how adversarial techniques in machine learning are involved in several of these new research frontiers.
Presented at ICLR2019
Видео Ian Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk) канала Steven Van Vaerenbergh
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Ian Goodfellow: Generative Adversarial Networks (NIPS 2016 tutorial)PyTorch at Tesla - Andrej Karpathy, TeslaYoshua Bengio | From System 1 Deep Learning to System 2 Deep Learning | NeurIPS 2019Fireside Chat with Daphne Koller (ICLR 2018)Ian Goodfellow: Generative Adversarial Networks (GANs) | Lex Fridman Podcast #19NeurIPS 2019 Outstanding New Directions Paper AwardISSCC 2019: Deep Learning Hardware: Past, Present, and Future - Yann LeCunIJCAI-ECAI 2018 | Yann LeCun | Learning World Models: the Next Step Towards AI.ICLR Debate with Leslie Kaelbling (ICLR 2019)Introduction to GANs, NIPS 2016 | Ian Goodfellow, OpenAIDavid Duvenaud | Reflecting on Neural ODEs | NeurIPS 2019AAAI-19 Invited Talk - Ian Goodfellow (Google AI) - Adversarial Machine LearningLecture 16 | Adversarial Examples and Adversarial TrainingBernhard Schölkopf: Learning Causal Mechanisms (ICLR invited talk)Heroes of Deep Learning: Andrew Ng interviews Ian GoodfellowNeural Ordinary Differential Equations - Best Paper Awards NeurIPS 2018Adversarial Machine Learning Ian GoodfellowYann LeCun - Power & Limits of Deep LearningJ. Z. Kolter and A. Madry: Adversarial Robustness - Theory and Practice (NeurIPS 2018 Tutorial)Few-Shot Video-to-Video Synthesis (NeurIPS 2019)