Soumitra Pandit
where else to find them
linkedin:soumitra-pandit-6062671a7
what they talk about
where they keep going back
no series more than once — all 1 in the filters
on a stage with
never shared a talk
who talks about the same things
- Adam Paszke6 talks
- Soumith Chintala13 talks
- Stephanie Kim3 talks
- Kimish Patel2 talks
- Wanchao Liang2 talks
- Mark Saroufim5 talks
| title | conference | date |
|---|---|---|
| DIY PyTorch - How to Learn Deeply | Optimized AI Conference 2025 | 2025-04-14 |
Explains how PyTorch’s implementation reduces deep learning to function composition and operator blocks, exposing a forward trace and an adjoint computational… | ||
| archive – Soumitra Pandit | Optimized AI Conference 2025 | 2025-04-14 |
Explains how PyTorch implements adjoint computational graphs so each operator block carries its backward rule and a forward pass becomes a trace that can be… | ||
| nothing matches | ||