Neural Networks in Cuda from Scratch - 2. Linear Layer
Автор: ThoenigAdrian
Загружено: 2022-09-23
Просмотров: 1302
In this part we will take care of computing the Linear Layer (weighted sum) and then feeding it into the activation function
The code can be found here: https://github.com/ThoenigAdrian/Neur...
If you are interested in general CUDA Programming, I can recommend the following the following resources:
Cuda Crash Course: @CoffeeBeforeArch • CUDA Crash Course: Vector Addition
Cuda Crash Cource v2: @CoffeeBeforeArch • C++ Crash Course (v2): Text Editors and Co...
NVIDIA CUDA Tutorial @Creel
• NVIDIA CUDA Tutorial 1: Introduction
Nvidia Documentation: https://docs.nvidia.com/cuda/cuda-c-p...
(Yes the official documentation, it's actually really good)
This will be a multipart series:
I am planning to cover the following topics
1. Implementing activation layer
2. Linear layer
3. Forward pass with multiple layers
4. Forward pass with multiple inputs
5. Backpropagation
6. Applying gradient descent
7. Training loop with multiple iterations
8. Cost function
9. Scaling
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
![Как сжимаются изображения? [46 МБ ↘↘ 4,07 МБ] JPEG в деталях](https://image.4k-video.ru/id-video/Kv1Hiv3ox8I)
![Физически-информированные нейронные сети (PINN) [Машинное обучение с учетом физики]](https://image.4k-video.ru/id-video/-zrY7P2dVC4)