[link]https://github.com/SuvrayanBandyopadhyay/TensorPlusPlus
Hey everyone,
Nowadays, everyone seems to be talking about Artificial Intelligence, especially with the rise of transformers and large language models. Due to this, it seems that everyone wants to become an ML "engineer" as soon as possible to profit from this trend.
Sadly, i have noticed that people around me blindly copy code without understanding how neural networks or tensors even work. Every project they do is just an api call to an llm like chatGPT.
Now while I am not against using libraries, I do believe some amount of knowledge about how things work is vital.
If you are like me, and you want to know more about how one can implement tensor mathematics and neural networks, check out this educational c++ library I have been working on
https://github.com/SuvrayanBandyopadhyay/TensorPlusPlus
Features (so far)
Basic Tensor operations (Addition, Subtraction, Matrix multiplication, Hadamard Product (Element-wise product)
Neural networks, with the following supported layers
- Dense
- RELU
- Leaky RELU
- Tanh
- Sigmoid
- Softmax
- Max - pooling
- Convolutional
Planed features
- RNNs
- Optimizers for the learning rate
I am still working on the documentation, but feel free to look at the code and let me know if you find any issues or bugs. If you have any suggestions or improvements please let me know in the comments.
Happy coding.
Top comments (0)