Chapter
Contextual Understanding of Language and Images by Neural Networks
36:39 - 42:53 (06:13)
The improvement in the neural networks used for natural language processing and image recognition has been achieved through the use of context in the form of a wide context to understand a word in context, or local context to understand a pattern in an image. Scaling up data and using better neural network architectures has improved prediction power.
Clips
The evolution of natural language processing has shown how scaling up the amount of data and utilizing better neural network architectures has led to better prediction results compared to human predictions.
36:39 - 40:05 (03:25)
Summary
The evolution of natural language processing has shown how scaling up the amount of data and utilizing better neural network architectures has led to better prediction results compared to human predictions. The technique of masking has been used to improve models like BERT and Roberta.
ChapterContextual Understanding of Language and Images by Neural Networks
Episode#206 – Ishan Misra: Self-Supervised Deep Learning in Computer Vision
PodcastLex Fridman Podcast
The understanding of a wide context can determine the meaning of a word in language, while a larger context is crucial in computer vision understanding local patterns in an image.
40:05 - 42:53 (02:48)
Summary
The understanding of a wide context can determine the meaning of a word in language, while a larger context is crucial in computer vision understanding local patterns in an image. The comprehension of elements within a context has contributed to the success of both fields.