Logo
 
Get An Intuitive Understanding of Deep Learning

Finally "GET" Deep Learning

Are you afraid of getting started with Deep Learning because it sounds too technical?

Have you been watching Deep Learning videos, but still don’t feel like you “get” it?

I’ve been there myself.

I built this course to save you many months of frustration trying to decipher Deep Learning. No other prep course needed - get started now.

Time commitment
  • 1-3 months
  • ~5-10 hrs/wk
Focus
  • Intuition & foundation
  • Math for deep learning
  • PyTorch + PyTorch Lightening
Prerequisites
  • Basic Python knowledge
  • High school math
Target audience

Who is this course for?

1.

Students who want learn Deep Learning for the first time

2.

Beginners who want to finally understand Deep Learning at an intuitive level

Prerequisites

What do you need before the course?

1.

Highschool math

2.

Basic Python or coding knowledge

What you'll learn

What will you know after taking this course?

1.

Develop an intuitive understanding of Deep Learning.

2.

You’ll be ready to explore the cutting edge of AI and more advanced neural networks like CNNs and Transformers

3.

You'll be able to understand what deep learning experts like Geoffrey Hinton and Andrej Karpathy are talking about in articles and interviews

4.

You’ll be able to start experimenting with your own AI projects using PyTorch

Course components

What's included in the course?

1.

Develop an intuitive understanding of deep neural networks

2.

Visual and intuitive understanding of core math concepts behind Deep Learning

3.

Detailed view of how exactly deep neural networks work beneath the hood

4.

Computational graphs (which libraries like PyTorch and Tensorflow are built on)

5.

Build neural networks from scratch using PyTorch and PyTorch Lightening

Course overview

Syllabus

Section 0

Deep learning - the big picture

  • What is machine learning exactly?
  • Different types of machine learning: supervised, unsupervised, and reinforcement learning
  • Deep neural network as features and weights
  • Loss functions
  • Training vs inference
  • Why deep learning is unintuitive and how to make it feel intuitive
Section 1

Reinventing the deep neural network from scratch

  • Perceptrons
  • Why it's called "deep" learning and why it matters
  • Activation functions
  • Cost of deep neural network's flexibility - the overfitting problem
  • Mystery of Deep Learning - "overparameterization"
  • Deep neural network as a Universal Function Approximator
  • Linear Algebra detour
  • The forward pass
  • Importance of scalability in deep learning models
  • Emergent properties of complex systems and why deep neural network is a black box
Section 2

How the model learns on its own - Back Propagation algorithm deep-dive

  • The naive method
  • The big picture - back propagation vs the naive method
  • Calculus detour - intuitive understanding of the core math behind back propagation
  • Gradient descent
  • Function composition and the chain rule
  • Computational graphs in depth
  • Back propagation under the hood
Section 3

How to make neural networks work in reality - intuition behind neural network optimizations

  • The Vanishing Gradient problem
  • Variations of gradient descent - Stochastic Gradient Descent and Mini-batch Gradient Descent
  • Gradient descent optimizers - Momentum, RMSProp, and Adam Optimizer
  • Learning rate decay, input normalization and batch norm
  • One of the most fundamental problems in Deep Learning: overfitting problem - the big picture
  • Solutions for overfitting - early stopping, regularization, and drop out
  • Neural networks with multiple outputs - softmax and cross entropy loss
  • All about data - importance of what goes into neural networks
Section 4

Coding deep neural networks in PyTorch and PyTorch Lightening

  • The basics - arrays, tensors, etc.
  • Build a simple neural network from scratch - math to code
  • Build the same neural network using PyTorch's nn module
  • Build a deep neural network to solve hand-written digit recognition problem using PyTorch and PyTorch Lightening

🎉Ready to get started?

Take the Udemy course now for $29.99.
Start learning today.

Learn

Get an intuitive understanding of Deep Learning and its underlying mechanics. Learn to build a neural network with PyTorch.

Time commitment

On average, students spend 1-3 months to complete this course.
© DeepIntuitions