- Books
- Online Courses
- Blogs to follow
- Popular AI/ML medium channel
- Popular Deep learning frameworks
- Concepts
- People to follow on Twitter
- Interactive Tools
- AI companies
- Machine Learning For Dummies Hands On Machine Learning with Scikit Learn and TensorFlow
- Introduction to Statistical Learning
- Practical Python and OpenCV + Case Studies
- Computer Vision: Models, Learning, and Inference
- Deep Learning by NPTEL
- A friendly introduction to Convolutional Neural Networks and Image Recognition
- Coursera - Convolutional Neural Networks
- Collection | Convolutional Neural Networks for Visual Recognition (Spring 2017)
- Udemy - Deep Learning and Computer Vision A-Z™ OpenCV, SSD & GANs
- Udemy - Deep Learning: Advanced Computer Vision
- Einstein AI
- Google AI blog
- WildML
- DistillPub (distillpub is unique, blog and publication both)
- Sebastian Ruder
- Jack Clark
- Prerequisite :
- Working knowledge of python.
- Basic experience with Numpy and pandas.
- Understanding of [RegEx](https://www.analyticsvidhya.com/blog/2015/06/regular-expression-python/
- Siraj Raval
- Delip Rao
- Geoffrey Hinton
- Andrew NG
- Fermat's Library
- Samim
- DynamicWebPaige
- Danilo J. Rezende
- Jane Wang
- Lex Fridman
- Soumith chinthala
- Jeremey Howard
- Hardmaru
Feature inversion to visualize millions of activations from an image classification network leads to an explorable activation atlas of features the network has learned. This can reveal how the network typically represents some concepts.
Available in many different languages.
New to Deep Learning? Tinker with a Neural Network in your browser.
Initialization can have a significant impact on convergence in training deep neural networks. Simple initialization schemes can accelerate training, but they require care to avoid common pitfalls. In this post, deeplearning.ai folks explain how to initialize neural network parameters effectively.
The best way to understand a neural network is to code it up from scratch!
Just like we use our brains to identify patterns and classify various types of information, deep learning algorithms can be taught to accomplish the same tasks for machines.
Example: Automatic car driving system is a good example of deep learning.
-
Why Deep Learning now?
Deep learning exits from 1970 but it became popular in the last 5 years due to the following reasons.
- More availability of Data
- Cheaper storage devices
- More computational power availability
- More optimized algorithms which takes less power and utilizes less resources.
- General concepts [ Tutorial | Interview questions ]
Machine Learning is a subset of AI and these are the algorithms which can learn by themselves without being externally programmed.
Example: Amazon using machine learning to give better product choice recommendations to there costumers based on their preferences. Netflix uses machine learning to give better suggestions to their users of the Tv series or movie or shows that they would like to watch.
- General concepts [ Tutorial | Interview questions ]
- Feature Engineering [ Tutorial | Interview questions ]
Artificial Intelligence is a ability of computer program to function like a human brain
Example: Robots like Sophia
- Computer Vision [ Tutorial | Interview questions ]
- Natural Language Processing [ Tutorial | Interview Questions ]
- Prediction [ Tutorial | Interview questions ]