In the last course, we built up a solid theoretical as well as a practical foundation on Machine Learning in general. Starting from this lesson, we will go further down the rabbit hole and learn about deep learning or deep neural networks.
Deep neural networks are a class of algorithms used for a large variety of Machine Learning tasks, including supervised learning. They are complex to understand, yet, they power most of the state-of-the-art Machine Learning and Artificial Intelligence solutions of the present decade.
Traditional Machine Learning algorithms such as decision trees or SVMs work pretty well on small datasets but as the amount of data gets larger and larger, such algorithms fail to show an increase in performance and their level of performance gets saturated. However, in the case of deep neural networks, the level of performance scales with the growth in the amount of available data.
In the present world, data is growing exponentially and thus, deep learning is gaining more popularity than ever before. Fortune-500 tech-companies such as Facebook, Google, etc. have been heavily investing in the research of new deep learning algorithms and thanks to them, we now also have open-sourced deep learning frameworks such as PyTorch and TensorFlow for Python.
This is the best time to start learning about deep neural networks and in this course, you will do just the same.
What is a deep neural network?
When you stack layers of inter-connected neurons one after another, it forms a deep neural network.
This is the most simple definition you can get out there. However, you may ask: What are neurons? How do you stack them layer after layer? What does a network of interconnected neurons mean?
You’ll get the answers to all of these questions by the time you reach the end of this course.
However, it is important to mention that this course teaches you about the most widely used type of deep neural network called a Dense Neural Network, or DNN, for short. And, in the next course, you will learn about another kind of deep neural network called a Convolutional Neural Network, or CNN, for short.
Once you have learned the theory behind the Dense Neural Network as well as the Convolutional Neural Network, you will be capable enough to learn about other kinds of neural networks on your own.
Do you want to learn Python, Data Science, and Machine Learning while getting certified? Here are some best selling Datacamp courses that we recommend you enroll in:
- Introduction to Python (Free Course) - 1,000,000+ students already enrolled!
- Introduction to Data Science in Python- 400,000+ students already enrolled!
- Introduction to TensorFlow for Deep Learning with Python - 90,000+ students already enrolled!
- Data Science and Machine Learning Bootcamp with R - 70,000+ students already enrolled!