Model Size Optimization
Lukas and Pete discuss techniques to reduce model size without compromising accuracy, including using convolution with a stride of two to save memory and the impact of quantization on memory sizes. Pete also shares insights on the challenges of lower bit depths due to hardware limitations.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Pete Warden — Practical Applications of TinyML
Related Questions
How does the size of a neural network affect its performance in deep learning, as discussed in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Introduction to Deep Double Descent?
How does the size of a neural network affect its performance in deep learning, as discussed in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Deep Double Descent?