Dive into Deep Learning with this free 15-hour YouTube Course
Deep Learning will help computer systems carry out human-like duties corresponding to speech recognition and picture classification.
With Deep Learning – a type of Machine Learning (Artificial Intelligence) – computer systems can extract and remodel knowledge utilizing a number of layers of neural networks.
You would possibly suppose that in an effort to use Deep Learning methods, you’d must know superior arithmetic, or have entry to highly effective computer systems.
Well so long as you’ve got handed highschool math, know the fundamentals of coding, and have a pc that is linked to the web, you’ll be able to be taught to do world-class Deep Learning.
We printed a 15-hour Deep Learning course on the freeCodeCamp.org YouTube channel with the objective of constructing Deep Learning accessible to as many individuals as potential.
The course is from quick.ai, and was developed by Jeremy Howard and Sylvain Gugger. Sylvain Gugger is a researcher who has written 10 math textbooks. And Jeremy has taught machine learning for the previous 30 years. He is the previous president and chief scientist of Kaggle, the world’s largest machine learning group.
After ending this course you’ll know:
- How to coach fashions that obtain state-of-the-art leads to laptop imaginative and prescient, pure language processing (NLP), tabular knowledge, and collaborative filtering
- How to show your fashions into internet purposes, and deploy them
- How Deep Learning fashions work
- How to make use of that data to enhance the accuracy, velocity, and reliability of your fashions
- The newest Deep Learning methods that actually matter in follow
- How to implement stochastic gradient descent and a whole coaching loop from scratch
- How to consider the moral implications of your work, and the way reduce the chance that your work is misused for hurt
Here are a number of the methods coated in this course:
- Random forests and gradient boosting
- Affine capabilities and nonlinearities
- Parameters and activations
- Random initialization and switch studying
- SGD, Momentum, Adam, and different optimizers
- Batch normalization
- Data augmentation
- Weight decay
- Image classification and regression
- Entity and phrase embeddings
- Recurrent neural networks (RNNs)
- And rather more
Watch the full course on the freeCodeCamp.org YouTube channel (15-hour watch).