In-Person PyTorch Workshop Facilitation
Budget: ₹1,250 – ₹2,500 INR
An in-person “Deep Learning with PyTorch” program kicks off in Bangalore during the first week of November. The audience—15 to 20 freshers and lateral hires—expects a fully immersive, workshop-driven experience that moves well beyond lectures.
Scope of work
• Design a concise, industry-relevant syllabus that introduces core deep-learning concepts and quickly shifts to practical PyTorch coding.
• Deliver hands-on workshops and live coding sessions each day, guiding participants through model creation, training, evaluation, and optimisation on real datasets.
• Build a capstone mini-project the group can complete by the final session to consolidate learning and serve as a portfolio piece.
Customised training assets
I’ll need branded slide decks, annotated Jupyter notebooks, datasets, and reference code bundled for easy post-class review. Feel free to mix printed quick-reference sheets with downloadable resources or a private Git repo—whatever best supports continued learning once the sessions end.
Logistics
Venue and core equipment will be arranged locally; bring any additional hardware or software licences you typically rely on for smooth demos. The timetable can run as an intensive boot camp or spread across several days that week—let’s align on what suits your teaching style while ensuring every participant leaves confident writing and deploying models in PyTorch.
To confirm fit, please share a brief outline of your proposed agenda and any prior examples of interactive PyTorch training you’ve led.
Topics -
Module 1- Logistic Regression Cross Entropy Loss
• Course Introduction
• Logistic Regression Cross Entropy Loss
Module 2- Softmax Regression
• Softmax
• Softmax Function: Using Lines to Classify Data Prediction
• Softmax PyTorch
Module 3- Shallow Neural Networks
• What's a Neural Network?
• More Hidden Neurons
• Neural Networks with Multiple Dimensional Input
• Multi-Class Neural Networks
• Backpropagation
• Activation Functions
Module 4- Deep Networks
• Deep Neural Networks
• Deeper Neural Networks: nn.ModuleList()
• Dropout
• Neural Network initialization Weights
• Gradient Descent with Momentum
• Batch Normalization
Module 5- Convolutional Neural Networks
• Convolution
• Activation Functions and Max Polling
• Multiple Input and Output Channels
• Convolutional Neural Network
• Convolutional Neural Network for MNIST
• Torch Vision Models
• Graphics Processing Unit
Scope of work
• Design a concise, industry-relevant syllabus that introduces core deep-learning concepts and quickly shifts to practical PyTorch coding.
• Deliver hands-on workshops and live coding sessions each day, guiding participants through model creation, training, evaluation, and optimisation on real datasets.
• Build a capstone mini-project the group can complete by the final session to consolidate learning and serve as a portfolio piece.
Customised training assets
I’ll need branded slide decks, annotated Jupyter notebooks, datasets, and reference code bundled for easy post-class review. Feel free to mix printed quick-reference sheets with downloadable resources or a private Git repo—whatever best supports continued learning once the sessions end.
Logistics
Venue and core equipment will be arranged locally; bring any additional hardware or software licences you typically rely on for smooth demos. The timetable can run as an intensive boot camp or spread across several days that week—let’s align on what suits your teaching style while ensuring every participant leaves confident writing and deploying models in PyTorch.
To confirm fit, please share a brief outline of your proposed agenda and any prior examples of interactive PyTorch training you’ve led.
Topics -
Module 1- Logistic Regression Cross Entropy Loss
• Course Introduction
• Logistic Regression Cross Entropy Loss
Module 2- Softmax Regression
• Softmax
• Softmax Function: Using Lines to Classify Data Prediction
• Softmax PyTorch
Module 3- Shallow Neural Networks
• What's a Neural Network?
• More Hidden Neurons
• Neural Networks with Multiple Dimensional Input
• Multi-Class Neural Networks
• Backpropagation
• Activation Functions
Module 4- Deep Networks
• Deep Neural Networks
• Deeper Neural Networks: nn.ModuleList()
• Dropout
• Neural Network initialization Weights
• Gradient Descent with Momentum
• Batch Normalization
Module 5- Convolutional Neural Networks
• Convolution
• Activation Functions and Max Polling
• Multiple Input and Output Channels
• Convolutional Neural Network
• Convolutional Neural Network for MNIST
• Torch Vision Models
• Graphics Processing Unit