Course Summary
This course will teach you how to build deep neural networks with PyTorch, an open-source machine learning library. Through hands-on exercises, you'll learn how to develop and train deep neural networks for a variety of applications.Key Learning Points
- Learn to build deep neural networks using PyTorch
- Develop a practical understanding of deep learning techniques
- Apply deep learning to real-world problems
Job Positions & Salaries of people who have taken this course might have
- Machine Learning Engineer
- USA: $112,000
- India: ₹1,080,000
- Spain: €40,000
- Data Scientist
- USA: $105,000
- India: ₹900,000
- Spain: €35,000
- Artificial Intelligence Researcher
- USA: $137,000
- India: ₹2,000,000
- Spain: €56,000
Related Topics for further study
Learning Outcomes
- Develop an understanding of deep learning techniques and their application
- Learn to build and train deep neural networks using PyTorch
- Apply deep learning to real-world problems
Prerequisites or good to have knowledge before taking this course
- Basic Python programming knowledge
- Familiarity with machine learning concepts
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
- Hands-on exercises
Similar Courses
- Neural Networks and Deep Learning
- Applied Data Science with Python
- Deep Learning Specialization
Related Education Paths
Related Books
Description
The course will teach you how to develop deep learning models using Pytorch. The course will start with Pytorch's tensors and Automatic differentiation package. Then each section will cover different models starting off with fundamentals such as Linear Regression, and logistic/softmax regression. Followed by Feedforward deep neural networks, the role of different activation functions, normalization and dropout layers. Then Convolutional Neural Networks and Transfer learning will be covered. Finally, several other Deep learning methods will be covered.
Outline
- Tensor and Datasets
- 1.0 Overview of Tensors
- 1.1 Tensors 1D
- 1.2 Two-Dimensional Tensors
- Differentiation in PyTorch
- 1.3 Simple Dataset
- 1.5 Dataset
- 1.1 Tensors 1D
- 1.2 Two-Dimensional Tensors
- 1.3 Derivatives in PyTorch
- Simple Dataset
- Datasets
- Linear Regression
- 2.1 Linear Regression Prediction
- 2.1 Linear Regression Training
- Loss
- Gradient Descent
- Cost
- Linear Regression PyToch
- PyTorch Linear Regression Training Slope and Bias
- Prediction in One Dimension
- Linear Regression Training
- Loss
- Gradient Descent
- Cost
- Training Parameters in PyTorch
- PyTorch Linear Regression Training Slope and Bias
- Linear Regression PyTorch Way
- Stochastic Gradient Descent
- Mini-Batch Gradient Descent
- Optimization in PyTorch
- Training, Validation and Test Split
- Training, Validation and Test Split PyTorch
- Quiz: Stochastic Gradient Descent
- Mini-Batch Gradient Descent
- 3.3 Optimization in PyTorch
- Training and Validation Data PyTorch
- Multiple Input Output Linear Regression
- Multiple Linear Regression Prediction
- Multiple Linear Regression Training
- Linear Regression Multiple Outputs
- Multiple Output Linear Regression Training
- Multiple Linear Regression Prediction
- Multiple Output Linear Regression
- Logistic Regression for Classification
- 5.0 Linear Classifiers
- 5.1 Logistic Regression: Prediction
- Bernoulli Distribution and Maximum Likelihood Estimation
- Logistic Regression Cross Entropy Loss
- 5.0 Linear Classifiers
- 5.0 Linear Classifiers
- 5.1 Logistic Regression: Prediction
- Bernoulli Distribution and Maximum Likelihood Estimation
- 5.3 Logistic Regression Cross Entropy Loss
- Softmax Rergresstion
- 6.1 Softmax
- 6.2 Softmax Function:Using Lines to Classify Data
- Softmax PyTorch
- 6.1 Softmax Function:Using Lines to Classify Data
- 6.2 Softmax Prediction
- 6.3 Softmax PyTorch Quizz
- Shallow Neural Networks
- What's a Neural Network
- More Hidden Neurons
- Neural Networks with Multiple Dimensional Input
- 7.4 Multi-Class Neural Networks
- 7.5 Backpropagation
- 7.5 Activation Functions
- Neural Networks
- More Hidden Neurons
- Neural Networks with Multiple Dimensional Inputs
- Multi-Class Neural Networks
- Backpropagation
- Activation Functions
- Deep Networks
- 8.1.1 Deep Neural Networks
- 8.1.2 Deeper Neural Networks : nn.ModuleList()
- 8.2 Dropout
- 8.3 Neural Network initialization Weights
- 8.4 Gradient Descent with Momentum
- Batch Normalization
- Deep Neural Networks
- Deeper Neural Networks : nn.ModuleList()
- Dropout
- Neural Network initialization
- Gradient Descent with Momentum
- Convolutional Neural Network
- 9.1 Convolution
- 9.2 Activation Functions and Max Polling
- 9.3. Multiple Input and Output Channels
- 9.4.1 Convolutional Neural Network
- 9.4.2 Convolutional Neural Network
- GPU in PyTorch
- TORCH-VISION MODELS
- 9.1 Convolution
- Activation Functions and Max Pooling
- Convolutional Neural Network
- Convolutional Neural Networks
- TORCH-VISION MODELS
- Peer Review
Summary of User Reviews
Key Aspect Users Liked About This Course
comprehensive and practical course materialPros from User Reviews
- Excellent instructors with clear and concise explanations
- Hands-on assignments and projects help to reinforce learning
- Great introduction to PyTorch and its applications in deep learning
Cons from User Reviews
- Some concepts may be difficult for beginners to grasp
- Course may be too fast-paced for those with no prior experience in deep learning
- Not enough emphasis on the mathematical foundations of deep learning
Joseph Santarcangelo
4.4 Raiting
Deep Learning with TensorFlow
- 4
-
![]()
![]()
![]()
![]()
![]()
Channel the power of deep learning with Google's TensorFlow! With deep learning going mainstream for making sense of data, getting accurate results using deep networks is possible....
Keras: Deep Learning in Python
- 3.7
-
![]()
![]()
![]()
![]()
![]()
Build complex deep learning algorithms easily in Python Do you want to build complex deep learning models in Keras?...
Hands - On Reinforcement Learning with Python
- 3.9
-
![]()
![]()
![]()
![]()
![]()
A practical tour of prediction and control in Reinforcement Learning using OpenAI Gym, Python, and TensorFlow The scope of Reinforcement Learning applications outside toy examples is immense....
Introduction to Embedded Machine Learning
- 4.8
-
![]()
![]()
![]()
![]()
![]()
Machine learning (ML) allows us to teach computers to make predictions and decisions based on data and learn from experiences. Introduction to Machine Learning...
