Data Science: Modern Deep Learning in Python from Udemy

Ever wondered how AI technologies like OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion really work? In this course, you will learn the foundations of these groundbreaking applications.

This course continues where my first course, Deep Learning in Python, left off. You already know how to build an artificial neural network in Python, and you have a plug-and-play script that you can use for TensorFlow. Neural networks are one of the staples of machine learning, and they are always a top contender in Kaggle contests. If you want to improve your skills with neural networks and deep learning, this is the course for you.

You already learned about backpropagation, but there were a lot of unanswered questions. How can you modify it to improve training speed? In this course you will learn about batch and stochastic gradient descent, two commonly used techniques that allow you to train on just a small sample of the data at each iteration, greatly speeding up training time.

You will also learn about momentum, which can be helpful for carrying you through local minima and prevent you from having to be too conservative with your learning rate. You will also learn about adaptive learning rate techniques like AdaGrad, RMSprop, and Adam which can also help speed up your training.

Because you already know about the fundamentals of neural networks, we are going to talk about more modern techniques, like dropout regularization and batch normalization, which we will implement in both TensorFlow and Theano. The course is constantly being updated and more advanced regularization techniques are coming in the near future.

In my last course, I just wanted to give you a little sneak peak at TensorFlow. In this course we are going to start from the basics so you understand exactly what's going on - what are TensorFlow variables and expressions and how can you use these building blocks to create a neural network? We are also going to look at a library that's been around much longer and is very popular for deep learning - Theano. With this library we will also examine the basic building blocks - variables, expressions, and functions - so that you can build neural networks in Theano with confidence.

Theano was the predecessor to all modern deep learning libraries today. Today, we have almost Keras, PyTorch, CNTK (Microsoft), MXNet (Amazon / Apache), etc. In this course, we cover all of these. Pick and choose the one you love best.

Because one of the main advantages of TensorFlow and Theano is the ability to use the GPU to speed up training, I will show you how to set up a GPU-instance on AWS and compare the speed of CPU vs GPU for training a deep neural network.

With all this extra speed, we are going to look at a real dataset - the famous MNIST dataset (images of handwritten digits) and compare against various benchmarks. This is THE dataset researchers look at first when they want to ask the question, "does this thing work?"

These images are important part of deep learning history and are still used for testing today. Every deep learning expert should know them well.

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

"If you can't implement it, you don't understand it"

Or as the great physicist Richard Feynman said: "What I cannot create, I do not understand".
My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch
Other courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?
After doing the same thing with 10 datasets, you realize you didn't learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times...

Suggested Prerequisites:

Know about gradient descent
Probability and statistics
Python coding: if/else, loops, lists, dicts, sets
Numpy coding: matrix and vector operations, loading a CSV file
Know how to write a neural network with Numpy

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

Check out the lecture "Machine Learning and AI Prerequisite Roadmap" (available in the FAQ of any of my courses, including the free Numpy course)

What's inside

Learning objectives

Apply momentum to backpropagation to train neural networks
Apply adaptive learning rate procedures like adagrad, rmsprop, and adam to backpropagation to train neural networks
Understand the basic building blocks of tensorflow
Build a neural network in tensorflow
Write a neural network using keras
Write a neural network using pytorch
Understand the difference between full gradient descent, batch gradient descent, and stochastic gradient descent
Understand and implement dropout regularization

Understand and implement batch normalization
Understand the basic building blocks of theano
Build a neural network in theano
Write a neural network using cntk
Write a neural network using mxnet
Understand important foundations for openai chatgpt, gpt-4, dall-e, midjourney, and stable diffusion
Show more
Show less

Apply momentum to backpropagation to train neural networks
Apply adaptive learning rate procedures like adagrad, rmsprop, and adam to backpropagation to train neural networks
Understand the basic building blocks of tensorflow
Build a neural network in tensorflow
Write a neural network using keras
Write a neural network using pytorch
Understand the difference between full gradient descent, batch gradient descent, and stochastic gradient descent
Understand and implement dropout regularization
Understand and implement batch normalization
Understand the basic building blocks of theano
Build a neural network in theano
Write a neural network using cntk
Write a neural network using mxnet
Understand important foundations for openai chatgpt, gpt-4, dall-e, midjourney, and stable diffusion
Show more
Show less

Syllabus

Introduction and Outline

Where to get the Code

How to Succeed in this Course

Review of basic neural network concepts, downloading MNIST, and using a linear classifier on it

Review (pt 1): Neuron Predictions

Review (pt 2): Neuron Learning

Review (pt 3): Artificial Neural Networks

Review Exercise Prompt

Review Code (pt 1)

Review Code (pt 2)

Review Summary

Know the difference between full, batch, and stochastic gradient descent, and their advantages and disadvantages

Stochastic Gradient Descent and Mini-Batch Gradient Descent (Theory)

SGD Exercise Prompt

Stochastic Gradient Descent and Mini-Batch Gradient Descent (Code pt 1)

Stochastic Gradient Descent and Mini-Batch Gradient Descent (Code pt 2)

Know how to use momentum and adaptive learning rates to improve backpropagation

How can you use momentum to speed up neural network training and get out of local minima?

Nesterov Momentum

Momentum in Code

Learn about periodic decay of learning rate, exponential decay, 1/t decay, AdaGrad, and RMSprop.

Constant learning rate vs. RMSProp in Code

Adam Optimization (pt 1)

Adam Optimization (pt 2)

Adam in Code

Suggestion Box

Choosing Hyperparameters

Hyperparameter Optimization: Cross-validation, Grid Search, and Random Search

Sampling Logarithmically

Grid Search in Code

Modifying Grid Search

Random Search in Code

Weight Initialization

Weight Initialization Section Introduction

Vanishing and Exploding Gradients

Local vs. Global Minima

Weight Initialization Section Summary

Understand Theano variables, expressions, and functions. Build a neural network in Theano.

Theano Basics: Variables, Functions, Expressions, Optimization

Building a neural network in Theano

Is Theano Dead?

Understand TensorFlow variables, expressions, and functions. Build a neural network in TensorFlow.

TensorFlow Basics: Variables, Functions, Expressions, Optimization

Building a neural network in TensorFlow

What is a Session? (And more)

Know how to use the GPU on Amazon Web Services to speed up backpropagation, and how to hone your deep learning skills.

I show you how to start a GPU instance on Amazon Web Services (AWS) and prove to you that training a neural network using Theano on the GPU can be much faster than the CPU.

Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer

Can Big Data be used to Speed Up Backpropagation?

How to Improve your Theano and Tensorflow Skills

Theano vs. TensorFlow

Transition to the 2nd Half of the Course

Project: Facial Expression Recognition

Facial Expression Recognition Project Introduction

Facial Expression Recognition Problem Description

The class imbalance problem

Utilities walkthrough

Class-Based ANN in Theano

Class-Based ANN in TensorFlow

Facial Expression Recognition Project Summary

Modern Regularization Techniques

Modern Regularization Techniques Section Introduction

Dropout Regularization

Dropout Intuition

Noise Injection

Modern Regularization Techniques Section Summary

Batch Normalization

Batch Normalization Introduction

Exponentially-Smoothed Averages

Batch Normalization Theory

Batch Normalization Tensorflow (part 1)

Batch Normalization Tensorflow (part 2)

Batch Normalization Theano (part 1)

Batch Normalization Theano (part 2)

Noise Perspective

Batch Normalization Summary

Keras

Keras Discussion

Keras in Code

Keras Functional API

How to easily convert Keras into Tensorflow 2.0 code

PyTorch

PyTorch Basics

PyTorch Dropout

PyTorch Batch Norm

PyTorch, CNTK, and MXNet

Deep Learning Review Topics

What's the difference between "neural networks" and "deep learning"?

Manually Choosing Learning Rate and Regularization Penalty

Setting Up Your Environment (FAQ by Student Request)

Pre-Installation Check

Anaconda Environment Setup

How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow

Extra Help With Python Coding for Beginners (FAQ by Student Request)

How to Code by Yourself (part 1)

How to Code by Yourself (part 2)

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Provides a strong foundation for those new to neural networks

Builds upon knowledge of basic neural network concepts

Focuses on 'how to build and understand', not just 'how to use'

Leverages Theano and TensorFlow

Instructs using Python code, which is beginner-friendly

Teaches critical principles of deep learning and AI

Reviews summary

Well-received deep learning course

Learners say this deep learning course is well-paced and easy to follow. According to students, the lectures are especially detailed and engaging

Students generally liked the pace of the course.

"Easy to listen to and just the right pace for my learning."

Lectures were lauded by students.

"Easy to listen to and just the right pace for my learning."

"The lectures on dropout and batch normalization are very detailed, as was the rest of the course."

Career center

Learners who complete Data Science: Modern Deep Learning in Python will develop knowledge and skills that may be useful to these careers:

Data Scientist

Data scientists analyze large datasets to extract meaningful insights, which can be used to improve decision-making and solve problems. They typically have a strong background in mathematics, statistics, and computer science. This course can help data scientists build a strong foundation in deep learning, which is a valuable skill for this field. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Data Scientist

Machine Learning Engineer

Machine learning engineers design and develop machine learning models, which can be used to automate tasks, make predictions, and improve decision-making. They typically have a strong background in computer science, mathematics, and statistics. This course can help machine learning engineers build a strong foundation in deep learning, which is a valuable skill for this field. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Machine Learning Engineer

Computer Vision Engineer

Computer vision engineers design and develop computer vision algorithms and technologies, which can be used to analyze and interpret images and videos. They typically have a strong background in computer science, mathematics, and statistics. This course can help computer vision engineers build a strong foundation in deep learning, which is a valuable skill for this field. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Computer Vision Engineer

Artificial Intelligence Researcher

Artificial intelligence researchers develop new and improved artificial intelligence algorithms and technologies. They typically have a strong background in computer science, mathematics, and statistics. This course can help artificial intelligence researchers build a strong foundation in deep learning, which is a valuable skill for this field. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Artificial Intelligence Researcher

Natural Language Processing Engineer

Natural language processing engineers design and develop natural language processing algorithms and technologies, which can be used to analyze and generate text. They typically have a strong background in computer science, linguistics, and mathematics. This course can help natural language processing engineers build a strong foundation in deep learning, which is a valuable skill for this field. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Natural Language Processing Engineer

Deep Learning Engineer

Deep learning engineers design and develop deep learning models, which can be used to automate tasks, make predictions, and improve decision-making. They typically have a strong background in computer science, mathematics, and statistics. This course can help deep learning engineers build a strong foundation in deep learning, which is a valuable skill for this field. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Deep Learning Engineer

Robotics Engineer

Robotics engineers design and develop robots, which can be used to automate tasks, perform dangerous jobs, and explore new environments. They typically have a strong background in computer science, mechanical engineering, and electrical engineering. This course can help robotics engineers build a strong foundation in deep learning, which is a valuable skill for this field. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Robotics Engineer

Financial Analyst

Financial analysts use mathematical and statistical models to analyze financial data and make investment decisions. They typically have a strong background in mathematics, statistics, and computer science. This course may be useful for financial analysts who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Financial Analyst

Quantitative Analyst

Quantitative analysts use mathematical and statistical models to analyze financial data and make investment decisions. They typically have a strong background in mathematics, statistics, and computer science. This course may be useful for quantitative analysts who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Quantitative Analyst

Actuary

Actuaries use mathematical and statistical models to assess risk and uncertainty. They typically have a strong background in mathematics, statistics, and computer science. This course may be useful for actuaries who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Actuary

Business Analyst

Business analysts help organizations improve their performance by analyzing data and identifying opportunities for improvement. They typically have a strong background in business, mathematics, and statistics. This course may be useful for business analysts who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Business Analyst

Operations Research Analyst

Operations research analysts use mathematical and statistical models to improve the efficiency and effectiveness of organizations. They typically have a strong background in mathematics, statistics, and computer science. This course may be useful for operations research analysts who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Operations Research Analyst

Statistician

Statisticians collect, analyze, and interpret data to make inferences about the world. They typically have a strong background in mathematics, statistics, and computer science. This course may be useful for statisticians who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Statistician

Data Analyst

Data analysts analyze data to extract meaningful insights, which can be used to improve decision-making and solve problems. They typically have a strong background in mathematics, statistics, and computer science. This course may be useful for data analysts who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Data Analyst

Software Engineer

Software engineers design, develop, and maintain software systems. They typically have a strong background in computer science. This course may be useful for software engineers who want to learn more about deep learning. The course covers topics such as gradient descent, backpropagation, and regularization, which are all essential for understanding and applying deep learning techniques.

See salaries and explore the career path for Software Engineer