{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/0512a28ce6ea4462ad60b55167165cdf\" frameborder=\"0\" width=\"1680\" height=\"1260\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1260,"width":1680,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1260,"thumbnail_width":1680,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/0512a28ce6ea4462ad60b55167165cdf-4255e2fa10a04071.gif","duration":275.043,"title":"9-Building Neural Networks from Scratch with NumPy 🤖","description":"In this video, I walk you through building a neural network from scratch using only NumPy, focusing on the fundamental concepts such as neurons, activation functions, loss functions, and backpropagation. We implement various activation functions and loss measures, and I demonstrate how to create a fully connected layer and a complete deep learning framework. I also showcase training on datasets like XOR, two moons, and MNIST, achieving a test accuracy of 97.2%. I encourage you to explore the notebook and see how the framework works in practice. Let's dive in and start building!"}