Description
The course will teach you how to develop deep-learning models using Pytorch. Then each section will cover different models starting 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.
Learning Outcomes: After completing this course, learners will be able to:
a). Explain and apply their knowledge of Deep Neural Networks and related machine learning methods
b). know how to use Python libraries such as PyTorch for Deep Learning applications
c). Build Deep Neural Networks using PyTorch
1. Tensor and Datasets
a). Overview of Tensors
b). Tensors 1D
c). Two-Dimensional Tensors
d). Differentiation in PyTorch
e). Simple Dataset
f). Dataset
g). Derivatives in PyTorch
2. Linear Regression
a). Linear Regression Prediction
b). Linear Regression Training
c). Loss
d). Gradient Descent
e). Linear Regression PyToch
f). PyTorch Linear Regression Training Slope and Bias
3. Linear Regression PyTorch Way
a). Stochastic Gradient Descent
b). Mini-Batch Gradient Descent
c). Optimization in PyTorch
4. Multiple Input Output Linear Regression
a). Multiple Linear Regression Prediction
b). Multiple Linear Regression Training
c). Linear Regression Multiple Outputs
d). Multiple Output Linear Regression
5. Logistic Regression for Classification
a). Linear Classifiers
b). Logistic Regression: Prediction
c). Bernoulli Distribution and Maximum Likelihood Estimation
d). Logistic Regression Cross Entropy Loss
6. Softmax Rergresstion
a). Softmax
b). Softmax Function: Using Lines to Classify Data
c). Softmax PyTorch
7. Shallow Neural Networks
a). What’s a Neural Network
b). More Hidden Neurons
c). Neural Networks with Multiple Dimensional Input
d). Multi-Class Neural Networks
e). Backpropagation
f). Activation Functions
8. Deep Networks
a). Deep Neural Networks
b). Deeper Neural Networks: nn.ModuleList()
c). Dropout
d). Neural Network initialization Weights
e). Gradient Descent with Momentum
f). Batch Normalization
9. Convolutional Neural Network
a). Convolution
b). Activation Functions and Max Polling
c). Multiple Input and Output Channels
d). Convolutional Neural Network
e). Convolutional Neural Network
f). GPU in PyTorch
g). TORCH-VISION MODELS
For more inputs on Deep Neural Networks with pytorch, you can connect here.
Contact the L&D Specialist at Locus IT.
Locus Academy has more than a decade of experience in delivering training/staffing on PyTorch for corporates across the globe. The participants for the training/staffing on PyTorch are delighted and can implement the learnings in their ongoing projects.
Reviews
There are no reviews yet.