A deep understanding of deep learning (with Python intro)

A deep understanding of deep learning (with Python intro), available at $109.99, has an average rating of 4.73, with 265 lectures, based on 4305 reviews, and has 35383 subscribers.

You will learn about The theory and math underlying deep learning How to build artificial neural networks Architectures of feedforward and convolutional networks Building models in PyTorch The calculus and code of gradient descent Fine-tuning deep network models Learn Python from scratch (no prior coding experience necessary) How and why autoencoders work How to use transfer learning Improving model performance using regularization Optimizing weight initializations Understand image convolution using predefined and learned kernels Whether deep learning models are understandable or mysterious black-boxes! Using GPUs for deep learning (much faster than CPUs!) This course is ideal for individuals who are Students in a deep learning course or Machine-learning enthusiasts or Anyone interested in mechanisms of AI (artificial intelligence) or Data scientists who want to expand their library of skills or Aspiring data scientists or Scientists and researchers interested in deep learning It is particularly useful for Students in a deep learning course or Machine-learning enthusiasts or Anyone interested in mechanisms of AI (artificial intelligence) or Data scientists who want to expand their library of skills or Aspiring data scientists or Scientists and researchers interested in deep learning.

Enroll now: A deep understanding of deep learning (with Python intro)

Summary

Title: A deep understanding of deep learning (with Python intro)

Price: $109.99

Average Rating: 4.73

Number of Lectures: 265

Number of Published Lectures: 265

Number of Curriculum Items: 265

Number of Published Curriculum Objects: 265

Original Price: $19.99

Quality Status: approved

Status: Live

What You Will Learn

The theory and math underlying deep learning

How to build artificial neural networks

Architectures of feedforward and convolutional networks

Building models in PyTorch

The calculus and code of gradient descent

Fine-tuning deep network models

Learn Python from scratch (no prior coding experience necessary)

How and why autoencoders work

How to use transfer learning

Improving model performance using regularization

Optimizing weight initializations

Understand image convolution using predefined and learned kernels

Whether deep learning models are understandable or mysterious black-boxes!

Using GPUs for deep learning (much faster than CPUs!)

Who Should Attend

Students in a deep learning course

Machine-learning enthusiasts

Anyone interested in mechanisms of AI (artificial intelligence)

Data scientists who want to expand their library of skills

Aspiring data scientists

Scientists and researchers interested in deep learning

Target Audiences

Students in a deep learning course

Machine-learning enthusiasts

Anyone interested in mechanisms of AI (artificial intelligence)

Data scientists who want to expand their library of skills

Aspiring data scientists

Scientists and researchers interested in deep learning

Deep learning is increasingly dominating technology and has major implications for society.

From self-driving cars to medical diagnoses, from face recognition to deep fakes, and from language translation to music generation, deep learning is spreading like wildfire throughout all areas of modern technology.

But deep learning is not only about super-fancy, cutting-edge, highly sophisticated applications. Deep learning is increasingly becoming a standard tool in machine-learning, data science, and statistics. Deep learning is used by small startups for data mining and dimension reduction, by governments for detecting tax evasion, and by scientists for detecting patterns in their research data.

Deep learning is now used in most areas of technology, business, and entertainment. And it’s becoming more important every year.

How does deep learning work?

Deep learning is built on a really simple principle: Take a super-simple algorithm (weighted sum and nonlinearity), and repeat it many many times until the result is an incredibly complex and sophisticated learned representation of the data.

Is it really that simple? mmm OK, it’s actually a tiny bit more complicated than that 馃槈   but that’s the core idea, and everything else literally everything else in deep learning is just clever ways of putting together these fundamental building blocks. That doesn’t mean the deep neural networks are trivial to understand: there are important architectural differences between feedforward networks, convolutional networks, and recurrent networks.

Given the diversity of deep learning model designs, parameters, and applications, you can only learn deep learning I mean, really learn deep learning, not just have superficial knowledge from a youtube video by having an experienced teacher guide you through the math, implementations, and reasoning. And of course, you need to have lots of hands-on examples and practice problems to work through. Deep learning is basically just applied math, and, as everyone knows, math is not a spectator sport!

What is this course all about?

Simply put: The purpose of this course is to provide a deep-dive into deep learning. You will gain flexible, fundamental, and lasting expertise on deep learning. You will have a deep understanding of the fundamental concepts in deep learning, so that you will be able to learn new topics and trends that emerge in the future.

Please note: This is not a course for someone who wants a quick overview of deep learning with a few solved examples. Instead, this course is designed for people who really want to understand how and why deep learning works; when and how to select metaparameters like optimizers, normalizations, and learning rates; how to evaluate the performance of deep neural network models; and how to modify and adapt existing models to solve new problems.

You can learn everything about deep learning in this course.

In this course, you will learn

Theory: Why are deep learning models built the way they are?

Math: What are the formulas and mechanisms of deep learning?

Implementation: How are deep learning models actually constructed in Python (using the PyTorch library)?

Intuition: Why is this or that metaparameter the right choice? How to interpret the effects of regularization? etc.

Python: If you’re completely new to Python, go through the 8+ hour coding tutorial appendix. If you’re already a knowledgeable coder, then you’ll still learn some new tricks and code optimizations.

Google-colab: Colab is an amazing online tool for running Python code, simulations, and heavy computations using Google’s cloud services. No need to install anything on your computer.

Unique aspects of this course

Clear and comprehensible explanations of concepts in deep learning, including transfer learning, generative modeling, convolutional neural networks, feedforward networks, generative adversarial networks (GAN), and more.

Several distinct explanations of the same ideas, which is a proven technique for learning.

Visualizations using graphs, numbers, and spaces that provide intuition of artificial neural networks.

LOTS of exercises, projects, code-challenges, suggestions for exploring the code. You learn best by doing it yourself!

Active Q&A forum where you can ask questions, get feedback, and contribute to the community.

8+ hour Python tutorial. That means you don’t need to master Python before enrolling in this course.

So what are you waiting for??

Watch the course introductory video and free sample videos to learn more about the contents of this course and about my teaching style. If you are unsure if this course is right for you and want to learn more, feel free to contact with me questions before you sign up.

I hope to see you soon in the course!

Mike

Course Curriculum

Chapter 1: Introduction

Lecture 1: How to learn from this course

Lecture 2: Using Udemy like a pro

Chapter 2: Download all course materials

Lecture 1: Downloading and using the code

Lecture 2: My policy on code-sharing

Chapter 3: Concepts in deep learning

Lecture 1: What is an artificial neural network?

Lecture 2: How models learn

Lecture 3: The role of DL in science and knowledge

Lecture 4: Running experiments to understand DL

Lecture 5: Are artificial neurons like biological neurons?

Chapter 4: About the Python tutorial

Lecture 1: Should you watch the Python tutorial?

Chapter 5: Math, numpy, PyTorch

Lecture 1: PyTorch or TensorFlow?

Lecture 2: Introduction to this section

Lecture 3: Spectral theories in mathematics

Lecture 4: Terms and datatypes in math and computers

Lecture 5: Converting reality to numbers

Lecture 6: Vector and matrix transpose

Lecture 7: OMG its the dot product!

Lecture 8: Matrix multiplication

Lecture 9: Softmax

Lecture 10: Logarithms

Lecture 11: Entropy and cross-entropy

Lecture 12: Min/max and argmin/argmax

Lecture 13: Mean and variance

Lecture 14: Random sampling and sampling variability

Lecture 15: Reproducible randomness via seeding

Lecture 16: The t-test

Lecture 17: Derivatives: intuition and polynomials

Lecture 18: Derivatives find minima

Lecture 19: Derivatives: product and chain rules

Chapter 6: Gradient descent

Lecture 1: Overview of gradient descent

Lecture 2: What about local minima?

Lecture 3: Gradient descent in 1D

Lecture 4: CodeChallenge: unfortunate starting value

Lecture 5: Gradient descent in 2D

Lecture 6: CodeChallenge: 2D gradient ascent

Lecture 7: Parametric experiments on g.d.

Lecture 8: CodeChallenge: fixed vs. dynamic learning rate

Lecture 9: Vanishing and exploding gradients

Lecture 10: Tangent: Notebook revision history

Chapter 7: ANNs (Artificial Neural Networks)

Lecture 1: The perceptron and ANN architecture

Lecture 2: A geometric view of ANNs

Lecture 3: ANN math part 1 (forward prop)

Lecture 4: ANN math part 2 (errors, loss, cost)

Lecture 5: ANN math part 3 (backprop)

Lecture 6: ANN for regression

Lecture 7: CodeChallenge: manipulate regression slopes

Lecture 8: ANN for classifying qwerties

Lecture 9: Learning rates comparison

Lecture 10: Multilayer ANN

Lecture 11: Linear solutions to linear problems

Lecture 12: Why multilayer linear models dont exist

Lecture 13: Multi-output ANN (iris dataset)

Lecture 14: CodeChallenge: more qwerties!

Lecture 15: Comparing the number of hidden units

Lecture 16: Depth vs. breadth: number of parameters

Lecture 17: Defining models using sequential vs. class

Lecture 18: Model depth vs. breadth

Lecture 19: CodeChallenge: convert sequential to class

Lecture 20: Diversity of ANN visual representations

Lecture 21: Reflection: Are DL models understandable yet?

Chapter 8: Overfitting and cross-validation

Lecture 1: What is overfitting and is it as bad as they say?

Lecture 2: Cross-validation

Lecture 3: Generalization

Lecture 4: Cross-validation manual separation

Lecture 5: Cross-validation scikitlearn

Lecture 6: Cross-validation DataLoader

Lecture 7: Splitting data into train, devset, test

Lecture 8: Cross-validation on regression

Chapter 9: Regularization

Lecture 1: Regularization: Concept and methods

Lecture 2: train() and eval() modes

Lecture 3: Dropout regularization

Lecture 4: Dropout regularization in practice

Lecture 5: Dropout example 2

Lecture 6: Weight regularization (L1/L2): math

Lecture 7: L2 regularization in practice

Lecture 8: L1 regularization in practice

Lecture 9: Training in mini-batches

Lecture 10: Batch training in action

Lecture 11: The importance of equal batch sizes

Lecture 12: CodeChallenge: Effects of mini-batch size

Chapter 10: Metaparameters (activations, optimizers)

Lecture 1: What are metaparameters?

Lecture 2: The wine quality dataset

Lecture 3: CodeChallenge: Minibatch size in the wine dataset

Lecture 4: Data normalization

Lecture 5: The importance of data normalization

Lecture 6: Batch normalization

Lecture 7: Batch normalization in practice

Lecture 8: CodeChallenge: Batch-normalize the qwerties

Lecture 9: Activation functions

Lecture 10: Activation functions in PyTorch

Instructors

Mike X Cohen
Educator and writer

Rating Distribution

1 stars: 20 votes

2 stars: 21 votes

3 stars: 163 votes

4 stars: 963 votes

5 stars: 3138 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!