Deep Learning for Beginner (AI) - Data Science
Learn Deep Learning from scratch. It is the extension of a Machine Learning, this course is for beginner who wants to learn the fundamental of deep learning and artificial intelligence. The course includes video explanation with introductions (basics), detailed theory and graphical explanations. Some daily life projects have been solved by using Python programming. Downloadable files of ebooks and Python codes have been attached to all the sections. The lectures are appealing, fancy and fast. They take less time to walk you through the whole content. Each and every topic has been taught extensively in depth to cover all the possible areas to understand the concept in most possible easy way. It's highly recommended for the students who don’t know the fundamental of machine learning studying at college and university level.
The main goal of publishing this course is to explain the deep learning and artificial intelligence in a very simple and easy way. All the codes have been conducted through colab which is an online editor. Python remains a popular choice among numerous companies and organization. Python has a reputation as a beginner-friendly language, replacing Java as the most widely used introductory language because it handles much of the complexity for the user, allowing beginners to focus on fully grasping programming concepts rather than minute details.
Below is the list of different topics covered in Deep Learning:
Introduction to Deep Learning
Artificial Neural Network vs Biological Neural Network
Activation Functions
Types of Activation functions
Artificial Neural Network (ANN) model
Complex ANN model
Forward ANN model
Backward ANN model
Python project of ANN model
Convolutional Neural Network (CNN) model
Filters or Kernels in CNN model
Stride Technique
Padding Technique
Pooling Technique
Flatten procedure
Python project of a CNN model
Recurrent Neural Network (RNN) model
Operation of RNN model
One-one RNN model
One-many RNN model
Many-many RNN model
Many-one RNN model
