On the Power of Forward pass through Transformer Architectures
https://youtu.be/JYt-ldZ3DqM New Technologies in Mathematics Seminar Speaker: Abhishek Panigrahi, Dept. of Computer Science, Princeton University Title: On the Power of Forward pass through Transformer Architectures Abstract: Highly trained transformers are capable of interesting computations as they infer for an input. The exact mechanism that these models use during forward passes is an interesting area of […]