Deep Learning Fundamentals Course Intro - Premium Edition
Deep Learning Fundamentals - Course Overview
Welcome to this deeplizard course on Deep Learning Fundamentals. If you are brand new to the field of deep learning and ready to learn all about artificial neural networks and how they're applied, then this course is for you!
Throughout this course, we'll cover concepts that are fundamental to deep learning and artificial neural networks. With the skills learned here, we'll gain the foundational understanding for what deep learning is, how it's applied, and the intuition for how to make use of it ourselves in code.
Applications of Deep Learning
Deep learning can be, and is, applied in a number of fields and real-world tasks. One of the earliest and most popular applications of deep learning has been in image classification, which we'll focus a lot on in this course.
This particular application of deep learning, however, is only the tip of the ice burg for what we can do with this technology currently and what we'll later be able to do with it in the future.
For example, self-driving cars use deep learning technology to detect and identify objects while driving.
Recommendations systems, such as those used by Netflix and YouTube to recommend which content you watch, also use artificial intelligent processes to do this.
The field of deep reinforcement learning, a sub-field of deep learning, has created artificially intelligent agents that play games such as chess, Go, Atari games, and Dota2 better than humans.
Generative adversarial networks, a specific type of artificial neural network, have been used to create art, 3D models, music, and even images of people that look extremely realistic, but actually do not exist!
The field of deep learning and artificial intelligence is extremely vast in the endless amounts of ways it can be introduced and applied in our lives, and it's rapidly growing and entering more and more fields everyday.
If you're interested in understanding these systems and how they use this technology, or you want to create new and innovative artificially intelligent based products or services yourself, then it's greatly important to first gain a foundational understanding of the fundamental topics in this field, and this course will help you get just that!
Since we'll be starting with the absolute deep learning basics, this course is great for beginners and requires no formal prerequisites!
In many lessons, we'll demonstrate new concepts with pseudocode to further our understanding of how these newly introduced ideas might be implemented in code.
By using pseudocode, we can demo new ideas in a programmatically intuitive way without depending on a specific programming language or API. Therefore, we don't necessarily need any programming experience to understand the pseudocode.
We have other great deep learning courses available that have a focus on coding, like our TensorFlow and PyTorch courses. We recommend taking these coding courses after learning the fundamentals in this course.
What You'll Learn
Perhaps you've already started your own research into understanding deep learning, and just in the first reading, you've come across concepts like perceptrons, gradient descent, backpropagation, convolutions, hyperparameters, transfer learning, data augmentation, and more.
It seems like an overwhelming amount of new technical topics to traverse all at once, but don't worry! We'll be covering all of these topics, plus many more, piece-by-piece to build a strong deep learning foundation for ourselves.
By taking this course, you will:
- Understand the relationship between AI, machine learning, and deep learning
- Learn about all of the components that make up an artificial neural network
- Learn all the steps involved with training artificial neural networks
- Gain an understanding for optimization, gradient descent, and backpropagation
- Understand the learnable parameters within an artificial neural network
- Learn about the different categories of datasets in deep learning: training, validation, test
- Understand how to detect problems during the network training process
- Learn techniques to improve network training
- Understand the different categories of learning: supervised, unsupervised, semi-supervised
- Learn how to work with and preprocess image data
- Gain an understanding for all the components in a convolutional neural network (CNN)
- Learn exactly how convolutions work with image data to detect patterns
- Understand problems that can occur during CNN training and potential solutions
- Learn how transfer learning works to transfer knowledge gained by one network to another
- Much more!
Be sure to check out the syllabus for full details about all the topics will cover in this course.
This course has plenty of resources to ensure your success. This is a premium course, and so to gain access to the contents, you must first register.
By registering for the course, you will unlock lifetime access to:
150pages of fully written corresponding lecture notes
- Custom-made quizzes following each lesson
- Exclusive access to the Discord server available only to students of this course
- Customized visual graphics created for this course
How to register for the course
Registration consists of two steps: creating an account on deeplizard.com and purchasing the course.
- Create a deeplizard account.
- Click the Login link on the top right of any page of deeplizard.com.
- Click create account.
- Enter a valid email address and password.
- Enter the verification code sent to your email address.
- Purchase the course.
- Ensure you're logged in to deeplizard.com.
- Browse to the course page.
- Click the Buy Now button.
- Agree to the Terms and Conditions.
- Enter your payment details. If you have a discount code, you may enter it here.
- Upon successful payment, the course will become unlocked, and you may view the full contents.
Below we have the course syllabus that outlines all of the topics we'll cover in this course. Check out the course page for more details on each lesson.
- Part 1: Deep Learning and Artificial Neural Networks
- Section 1: Intro to Deep Learning
- Deep Learning Fundamentals Course Introduction
- AI vs. Machine Learning vs. Deep Learning - Relationship Overview
- Intro to Deep Learning
- Section 2: Artificial Neural Networks
- Perceptrons Explained - Deep Learning
- Intro To Artificial Neural Networks
- Layers in Artificial Neural Networks Explained
- Activation Functions in Artificial Neural Networks Explained
- Loss Functions in Artificial Neural Networks Explained
- Training Artificial Neural Networks Explained
- Batch Size & Epochs in Artificial Neural Networks Explained
- Optimization Algorithms in Artificial Neural Networks Explained
- Learning Rates in Artificial Neural Networks Explained
- Backpropagation Intuition - Neural Network Training Explained
- Bias in Artificial Neural Networks Explained
- Learnable parameters in Artificial Neural Networks Explained
- Section 3: Additional Fundamental topics
- Datasets for Deep Learning - Training, Validation, & Test Sets Explained
- Overfitting Explained - Artificial Neural Networks
- Underfitting Explained - Artificial Neural Networks
- Data Augmentation in Deep Learning Explained
- Regularization in Deep Learning Explained
- Supervised Learning Explained
- Unsupervised Learning Explained
- Semi-supervised Learning Explained
- Part 2: Convolutional Neural Networks (CNNs)
- Section 1: Image Data Preprocessing
- One-hot Encoded Categorical Labels for Deep Learning Explained
- Image Data Pre-processing for Neural Networks Explained
- Image Data As Neural Network Input Explained - Deep Learning
- Section 2: How CNNs work
- Convolutional Neural Networks (CNNs) Explained
- Convolutions in Deep Learning - Interactive Demo App
- How Convolutional Filters Detect Patterns - CNNs Explained
- Convolutional Layers vs. Fully Connected Layers Explained - Deep Learning
- Zero Padding in Neural Networks Explained
- Max Pooling in Neural Networks Explained
- Max Pooling in Deep Learning - Interactive Demo App
- Batch Normalization in Neural Networks Explained
- Learnable Parameters in Convolutional Neural Networks Explained
- Section 3: Additional Fundamental Topics
- Transfer Learning & Fine-tuning Neural Networks Explained
- Neural Network Vanishing Gradient Problem with Backpropagation Explained
- Neural Network Weight Initialization Explained
- Deep Learning Fundamentals Course Conclusion
I hope you're looking forward to the course! Let's jump in!
Committed by on