Neural Networks for Computer Vision, Time Series Forecasting, NLP, GANs, Reinforcement Learning, and More!
What you'll learn
- Artificial Neural Networks (ANNs) / Deep Neural Networks (DNNs)
- Predict Stock Returns
- Time Series Forecasting
- Computer Vision
- How to build a Deep Reinforcement Learning Stock Trading Bot
- GANs (Generative Adversarial Networks)
- Recommender Systems
- Image Recognition
- Convolutional Neural Networks (CNNs)
- Recurrent Neural Networks (RNNs)
- Natural Language Processing (NLP) with Deep Learning
- Demonstrate Moore's Law using Code
- Transfer Learning to create state-of-the-art image classifiers
- Know how to code in Python and Numpy
- For the theoretical parts (optional), understand derivatives and probability
Tensorflow has gained massive popularity over the past few years, but PyTorch has been the library of choice for deep learning and artificial intelligence researchers and professionals around the world.
Is it possible that Tensorflow is popular only because Google is popular and used effective marketing?
What changed so wildly between versions 1 and 2 of Tensorflow? Were there any major flaws in it, and are there still issues?
The fact that PyTorch is backed by another Internet giant, Facebook (specifically, the Facebook AI Research Lab – FAIR), is less widely known. If you want an open source deep learning library backed by billion dollar companies and lots of community support, you can't go wrong with PyTorch. Plus, you can't ruin all your old code when it upgrades to the next version. 😉
All the top AI shops (ex. OpenAI, Apple, and JPMorgan Chase) use PyTorch. OpenAI just switched to PyTorch in 2020, a strong sign that PyTorch is on the rise.
It is easy to build and test new ideas with PyTorch, whereas other libraries that try to do everything for you can be hard. Oh, and PyTorch is faster.
Deep Learning has been responsible for some amazing achievements recently, such as:
- Generating beautiful, photo-realistic images of people and things that never existed (GANs)
- Beating world champions in the strategy game Go, and complex video (aff) games like CS:GO and Dota 2 (Deep Reinforcement Learning)
- Self-driving cars (Computer Vision)
- Speech recognition (e.g. Siri) and machine translation (Natural Language Processing)
- Even creating videos (aff) of people doing and saying things they never did (DeepFakes – a potentially nefarious application of deep learning)
This PyTorch: Deep Learning and Artificial Intelligence course is for beginner-level students all the way up to expert-level students. How can this be?
In the main PyTorch: Deep Learning and Artificial Intelligence course, you will learn about all of the major deep learning architectures, such as the Deep Neural Network, Convolutional Neural Network, and Recurrent Neural Network.
Current projects include:
- Natural Language Processing (NLP)
- Recommender Systems
- Transfer Learning for Computer Vision
- Generative Adversarial Networks (GANs)
- Deep Reinforcement Learning Stock Trading Bot
Although you have taken all of my previous courses, you will still learn about converting your code to PyTorch, and there will be all-new and never-before-seen projects in this PyTorch: Deep Learning and Artificial Intelligence course such as time series forecasting and stock predictions.
The PyTorch: Deep Learning and Artificial Intelligence course is designed for students who are looking to learn quickly, but there is also a “deeper dive into theory” section for those who would like to dig a little deeper (like what is a loss function, and what are the different types of gradient descent approaches).
Although you may not be 100% comfortable with the mathematical concepts, you can still do this! In this course, we focus on PyTorch instead of deriving any mathematical equations. I already have several PyTorch: Deep Learning and Artificial Intelligence courses on that already, so there is no need to repeat that here.
Instructor's Note: This PyTorch: Deep Learning and Artificial Intelligence course focuses on breadth rather than depth, with less theory in favor of building more cool stuff. If you are looking for a more theory-dense course, this is not it. Generally, for each of these topics (recommender systems, natural language processing, reinforcement learning, computer vision, GANs, etc.) I already have courses singularly focused on those topics.
Thanks for reading, and I’ll see you in class!
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 PyTorch: Deep Learning and Artificial Intelligence courses, including the free Numpy course)
Who this course is for:
- Beginners to advanced students who want to learn about deep learning and AI in PyTorch
Created by Lazy Programmer Team, Lazy Programmer Inc.
Last updated 4/2021
Size: 7.28 GB