Chapter
Techniques for Computer Vision, Speech and Natural Language Understanding
1:12:28 - 1:22:04 (09:36)
This podcast discusses the various techniques used for computer vision, speech recognition and natural language understanding, including end-to-end deep learning systems, convolutional nets, and conventional computer vision techniques.
Clips
The podcast discusses the practical interests of AI research such as active learning and reinforcement learning versus fundamental research like multitask learning and continual learning.
1:12:28 - 1:19:27 (06:59)
AI Research
Summary
The podcast discusses the practical interests of AI research such as active learning and reinforcement learning versus fundamental research like multitask learning and continual learning.
ChapterTechniques for Computer Vision, Speech and Natural Language Understanding
Episode#258 – Yann LeCun: Dark Matter of Intelligence and Self-Supervised Learning
PodcastLex Fridman Podcast
The standard way of training deep learning systems for speech recognition, OCR, image recognition, and natural language understanding nowadays is end to end, with the system learning its own features.
1:19:29 - 1:22:04 (02:34)
Deep Learning
Summary
The standard way of training deep learning systems for speech recognition, OCR, image recognition, and natural language understanding nowadays is end to end, with the system learning its own features. Previously, a good front end was necessary to pre-process signals before training the system.