Neural Networks Made Easy
- Be able to code in Python with NumPy and Pandas
Wanna understand deep learning and neural networks so well, you could code them from scratch? In this course, we'll do exactly that.
The course starts by motivating and explaining perceptrons, and then gradually works its way toward deriving and coding a multiclass neural network with stochastic gradient descent that can recognize hand-written digits from the famous MNIST dataset.
This course is all about understanding the fundamentals of neural networks. So, it does not discuss TensorFlow, PyTorch, or any other neural network libraries. However, by the end of this course, you should understand neural networks so well that learning TensorFlow and PyTorch should be a breeze!
In this course, I present a number of coding challenges inside the video lectures. The general approach is, we'll discuss an idea and the theory behind it, and then you're challenged to implement the idea / algorithm in Python. I'll discuss my solution to every challenge, and my code is readily available on github.
In this course, we'll be using Python, NumPy, Pandas, and good bit of calculus. ..but don't let the math scare you. I explain everything in great detail with examples and visuals.
If you're rusty on your NumPy or Pandas, check out my free courses Python NumPy For Your Grandma and Python Pandas For Your Grandpa.
Who this course is for:
- People interested in learning how neural networks work
Hi I’m Ben. I spent five years doing actuarial work for an insurance company before ditching the cubicle and opening up my freelance machine learning consultancy, GormAnalysis. Now I build predictive models for companies spanning a range of industries including insurance, ecommerce, tech, real estate, and others. I'm also a Kaggle Master, for whatever that's worth..
I've been blogging about technical machine learning topics for years, but since I personally prefer learning from videos, I decided to upgrade my blog into video format. You see, these courses are not intended for you; they're a reference for future me, when I forget how things work. But you can use them too, for a small fee :)