This online course will get you started in creating your first artificial neural network using deep learning techniques. Following previous course on logistic regression, take this basic building block, and create full-on non-linear neural networks right out of the gate using Python and Numpy. You will get all the materials for this course are completely free.
This will help you in extending the previous binary classification model to multiple classes using the softmax function, and deriving the very important training method called “backpropagation” using first principles. It will show you how to code backpropagation in Numpy, first “the slow way”, and then “the fast way” using Numpy features.
Next thing, you have to do implement a neural network using Google’s new TensorFlow library.
You must get this course if you are interested in beginning your journey toward becoming a master at deep learning, or if you are interested in machine learning and data science in general. You have to go beyond basic models like logistic regression and linear regression and it will show you something that automatically learns features.
This course provides you with many practical examples so that you can really know how deep learning can be used on anything. Throughout the course, you will learn with the course project how to predict user actions on a website given user data like whether or not that user in on a mobile device, the number of products they viewed, how long they stayed on your website, whether or not they are returning visitor, and what time of the day they visited.
At the end of the course another project will show how you can use deep learning for facial expression recognition and how to imagine being able to predict someone’s emotions just based on a picture!
After getting your feet wet with the fundamentals things, you will be provided a brief overview of some of the newest developments in neural networks – slightly modified architectures and why they are used for.
If you already know about softmax and backpropagation, and you are willing to skip over the theory and speed things up using more advanced techniques along with GPU-optimization, look out follow-up course on this topic “Data Science: Practical Deep Learning Concepts in Theano and TensorFlow“.
Look out other courses that cover more advanced topics like Convolutional Neural Networks, Restricted Boltzmann Machines, Autoencoders, and more! But you need to be very comfortable with the material in this course before moving on to more advanced topics.
This course purely focuses on “how to build and understand“, not just “how to use”. Anyone can learn how to use an API in 15 minutes after reading some documentation. It’s not about remembering facts in fact, it’s about “seeing for yourself” via experimentation. It will let you know how to visualize what’s happening in the model internally. If you need more than just a superficial look at machine learning models, this course is the best for you.
You can download all the code from github:/lazyprogrammer/machine_learning_examples
In the directory: ann_class
You need to make sure you always “git pull” so that you have the latest version!
HARD PREREQUISITES / KNOWLEDGE YOU ARE ASSUMED TO HAVE:
- Linear algebra
- Python coding: if/else, loops, lists, dicts, sets
- Numpy coding: matrix and vector operations, loading a CSV file
If you need more details about this course, visit here-> Data Science – Deep Learning in Python