Roko Mijic - Putin Alignment
From the New World
The Future of Architecture in Machine Learning
They discuss the future of architecture in machine learning, focusing on variations of transformers and the ongoing progress in making MNIST classifiers more reliable. They suggest future advancements may involve heavy modifications to gradient descent optimizers and optimizing for complex auxiliary loss functions.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
