/Neural-Network-from-Scratch

Building a deep neural network only using numpy

Primary LanguageJupyter Notebook

Neural-Network-from-Scratch

Building a deep neural network only using numpy

I found that directly using libabries such as tensorflow, pytorch, and sklearn made it difficult to fundementally understand the math and inner workings of neural networks. Therefore, I decided to build one from scratch only using numpy in order to gain a more intuitive understanding of neural networks.

Logistic Regression Model

Planning on including:

  • AdaM Optimization (RMS Prop & momentum)
  • Mini Batch gradient descent
  • Regularization (L2 & Dropout)
  • Learning Rate Decay