Data Science: Deep Learning and Neural Networks in Python is the name of the Neural Networks and Deep Learning Bootcamp published by Udemy Academy. This course will get you started building your first artificial neural network using deep learning techniques and building full nonlinear neural networks using Python and Numpy. This course extends the previous binary classification model to multiple classes using the softmax function and derives a very important training method called “backpropagation” using first principles.
It will show you how to find first the “slow way” and then the “fast way” in Numpy coding using Numpy features. Then, it implements a neural network using Google’s new TensorFlow library. If you are interested in starting your journey to becoming a deep learning master, or if you are interested in machine learning and data science in general, you should take this course. We’re going beyond basic models like logistic regression and linear regression, and I’m going to show you something that automatically learns features.
This course gives you lots of practical examples so you can really see how deep learning can be used in anything. During the course, we will do a course project, which will show you how to predict user actions on a website given user data, such as whether that user is on a mobile device or not. , the number of products viewed, the duration of their stay. on your site, whether they are returning visitors or not, and what time of day they visited.
Another project at the end of the course will show you how you can use deep learning for facial expression recognition. Imagine being able to predict someone’s feelings based on just one photo! After familiarizing yourself with the basics, a brief overview of some of the most recent developments in neural networks—slightly modified architectures and their use cases—is presented.
What you will learn in the Data Science: Deep Learning and Neural Networks in Python course:
- Learn how deep learning really works
- Learn how a neural network is built from the basic building blocks (neurons).
- Code a neural network from scratch in python and numpy
- Coding a neural network using Google’s TensorFlow
- Describe the different types of neural networks and the different types of problems they are used for
- Derive the backpropagation law from first principles
- Create a neural network with output with K>2 classes using softmax software
- Explain the various terms associated with neural networks such as “activation”, “backpropagation” and “feedforward”.
- Install TensorFlow
Moderator: Lazy Programmer Inc.
Education level: introductory to advanced
Number of courses: 89
Duration of training: 11 hours and 13 minutes
Data Science Course headings
Being familiar with the content of my logistic regression course (cross-entropy cost, gradient descent, neurons, XOR, donut) will give you the proper context for this course
Data Science Course images
After Extract, view with your favorite Player.