A neural network for predicting handwritted digits made from scratch in pure mojo
Implements:
- Gradient Descent
- Backpropogation
- Forward Propogation
- Sigmoid Activation
- ReLU Activation
- Deriv ReLU
- One-hot Encoding
- Getting Predictions/Accuracy
- File Loader
- Index, Coordinate System w/ Tensors
- Tensor Transposition
- Matrix Shuffling (SIMD)
- Exp Application (SIMD)
- Summation Functions (SIMD)
- Adding / Dividing Vectors (SIMD, Parallelization)
- Matrix Multiplication (SIMD, Parallelization)
- Data Copying (SIMD)