Deep learning is a new subset of machine learning concerned with algorithms inspired by the human brain's structure and functionality. Deep learning has attracted a lot of attention because it is particularly suitable for supervised learning that is potentially useful for most real-world applications. It is a groundbreaking tool for processing large volumes of data since the deep-learning algorithms' performance increases as they experience more data. Deep learning is similar to classical machine learning algorithms in terms of functionality, and it differs in terms of capabilities and flexibility. It is evolving as one of the crucial practices in industries like manufacturing, health care, digital assistants, automotive, etc.
TechClass Fundamentals of Deep Learning online course provides a unique opportunity for you to get familiar with the basic concepts of deep learning. Throughout this course, you will get familiar with different deep learning architectures and models and their intuitions as well as variations of the neural network algorithm used for various types of data. By the end of this course, you can state your deep learning-based attitude toward business problems using critical concepts and techniques of deep learning in today's industry discussed in the course.
Learning outcomes
- Learn the basic concepts and definitions of deep learning and its applications
- Learn the differences between machine learning and deep learning
- Get familiar with the primary types of deep learning methods
- Get familiar with basic concepts of the Neural Network algorithm such as wight and neuron
- Understand the concepts and intuitions of neural network algorithm
- Get familiar with the history of deep learning and the reasons and motives behind its advent
- Get familiar with the steps of training and evaluating neural networks
- Learn about the concepts of regularization, overfitting, and hyperparameters selection
- Learn about the layers of convolutional neural networks (CNNs) and their functionalities
- Get familiar with the popular CNN architectures
- Learn the intuitions of recurrent neural networks (RNNs) and how they perform
- Get familiar with variations of RNNs and the differences between them
- Get familiar with the choice of deep networks for different types of tasks
- Get familiar with transfer learning, generative adversarial networks, and autoencoders
Table of contents
Chapter 1: Intro to Course
- 1.1. Welcome!
- 1.2. About TechClass Data Science Department
- 1.3. Learning Outcomes
- 1.4. Your Expectations, Goals, and Knowledge
- 1.5. Abbreviations
- 1.6. Copyright Notice
Chapter 2: Introduction to Machine Learning
- 2.1. The Concept of Learning
- 2.2. Data
- 2.3. Machine Learning
- 2.4. Supervised Learning
- 2.5. Unsupervised Learning
- 2.6. Applications
Chapter 3: Introduction to Deep Learning
- 3.1. What is Deep Learning?
- 3.2. Deep Learning Architectures
- 3.3. Deep Learning vs. Machine Learning
- 3.4. Artificial Neural Network vs. Biological Neural Network
- 3.5. History of Deep Learning
Chapter 4: Feed-Forward Neural Networks
- 4.1. A Single Neuron
- 4.2. Neural Networks
- 4.3. Activation Functions in Neural Networks
- 4.4. Training Neural Networks
- 4.5. Prediction and Evaluation
- 4.6. Bias and Variance
- 4.7. Regularization
- 4.8. Model Selection and Hyperparameters
Chapter 5: Convolutional Neural Networks
- 5.1. Motivation for Convolutional Layers
- 5.2. Convolutional Layer
- 5.3. Pooling Layer
- 5.4. Convolutional Networks
- 5.5. Analogy Between CNNs and Human Visual System
- 5.6. Popular CNN Architectures
- 5.7. Applications
Chapter 6: Sequence Models
- 6.1. Motivation for Sequence Models
- 6.2. Recurrent Neural Networks
- 6.3. Variations of RNN
- 6.4. Encoder-Decoder
- 6.5. Attention Mechanism
- 6.6. Applications
Chapter 7: What’s More?
- 7.1. Transfer Learning
- 7.2. Autoencoders
- 7.3. Generative Adversarial Networks
- 7.4. Deep Learning Frameworks
Chapter 8: Final Tasks
- 8.1. Project
- 8.2. Self-study Essay
Chapter 9: Finishing the Course
- 9.1. What We Have Learned
- 9.2. Where to Go Next?
- 9.3. Your Opinion Matters
- 9.4. Congrats! You did it!
Brochure
