Learn the most in-depth process for defining and programming neural networks with pure Python and Tensorflow
What you'll learn
- Learn how Deep Learning REALLY works (not just some diagrams and magical black box code)
- Learn how a neural network is built from basic building blocks (the neuron)
- Code a neural network from scratch in Python and numpy
- Code a neural network using Google's TensorFlow
- Describe different types of neural networks and the different types of problems they are used for
- Derive the backpropagation rule from first principles
- Create a neural network with an output that has K > 2 classes using softmax
- Describe the various terms related to neural networks, such as “activation”, “backpropagation” and “feedforward”
- Install TensorFlow
- Basic math (calculus derivatives, matrix arithmetic, probability)
- Install Numpy and Python
- Don't worry about installing TensorFlow, we will do that in the lectures.
- 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 Data Science: Deep Learning and Neural Networks in Python course
By the end of this Data Science: Deep Learning and Neural Networks in Python course, you will have designed your own artificial neural network using deep learning techniques. We take this basic building block, and we deconstruct non-linear neural networks using Python and Numpy, in the same way that we used logistic regression previously. This Data Science: Deep Learning and Neural Networks in Python course's materials are completely free.
Our previous binary classification model is extended to multiple classes using the softmax function, and we derive one of the most important training methods called “backpropagation” from first principles. How to use Numpy's fast and slow backpropagation methods. First I show you how to do it “the slow way,” then I show you how to do it “the fast way.”
Using the new TensorFlow library from Google, we implement a neural network.
If you are interested in taking the first step towards becoming a master at deep learning, or if you are interested in data science and machine learning in general, this Data Science: Deep Learning and Neural Networks in Python course is for you. As we continue, we will examine something beyond simple models like logistic regression and linear regression and I will show you how it can automatically learn features.
With this course, you will experience a wide range of practical examples to illustrate how deep learning can be applied to a huge range of real-world problems. The Data Science: Deep Learning and Neural Networks in Python course will involve a project where you will learn how to predict user actions on a website (aff) based on information like the user's mobile device, the number of products they view, how long they stay on the site (aff), if they are returning, and what time of day they visit.
In the final project of the Data Science: Deep Learning and Neural Networks in Python course, you will learn how to recognize facial expressions using deep learning. It would be an amazing feat to be able to interpret emotions based on a picture alone.
I review the fundamentals of neural networks and briefly describe some of the latest developments in its architectures and applications following a brief overview of the basics.
I have a follow-up Data Science: Deep Learning and Neural Networks in Python course on this topic, Data Science: Practical Deep Learning Concepts in Theano and TensorFlow, if you want to skip over the theory and learn about more advanced techniques as well as GPU optimization.
In addition to these courses, I have other classes on advanced topics, such as Convolutional Neural Networks, Restricted Boltzmann Machines, Autoencoders, and others. Prior to studying more advanced topics, you should make sure you are comfortable with the material in this Data Science: Deep Learning and Neural Networks in Python course.
In this course, students learn “how to build and understand”, not just “how to use.”. A few minutes of reading some documentation is all an API user needs to learn how to use it. By experimenting, you don't just remember the facts, you get to “see for yourself.” In this Data Science: Deep Learning and Neural Networks in Python course, you will learn how to visualize what's happening internally in the model. If you are interested in learning more than just the superficial details of machine learning models, this course is for you.
“If you can't implement it, you don't understand it”
- Or as the great physicist Richard Feynman said: “What I cannot create, I do not understand”.
- My Data Science: Deep Learning and Neural Networks in Python courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch
- Other Data Science: Deep Learning and Neural Networks in Python courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?
- After doing the same thing with 10 datasets, you realize you didn't learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times…
- calculus (taking derivatives)
- matrix arithmetic
- Python coding: if/else, loops, lists, dicts, sets
- Numpy coding: matrix and vector operations, loading a CSV file
- Be familiar with basic linear models such as linear regression and logistic regression
WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:
- Visit the lecture “Machine Learning and AI Prerequisite Roadmap” (available in the FAQ of any of my courses, including the free Numpy course) for more information.
Who this course is for:
- Students interested in machine learning – you'll get all the tidbits you need to do well in a neural networks course
- Professionals who want to use neural networks in their machine learning and data science pipeline. Be able to apply more powerful models, and know its drawbacks.
Created by Lazy Programmer Inc.
Last updated 5/2021
Size: 1.8 GB