Programme Parameters
Graduate / Intermediate
5 Weeks (50 Hrs)
Online (e-LMS)
• A basic understanding of the subject area and fundamental programming or scientific concepts.
• A laptop or desktop with a stable internet connection.
• Willingness to complete assignments and the capstone project.
About This Course
This program introduces the core concepts of deep learning, focusing on neural network architectures, optimization techniques, and common applications. Across 5 Weeks, you will work hands-on with neural network architectures and optimization techniques, then consolidate everything in a capstone project. Every participant receives a verified e-Certificate and e-Marksheet from the Deep Science & Technology Consortium.
🎯 Program Aim
This program introduces the core concepts of deep learning, focusing on neural network architectures, optimization techniques, and common applications.
📋 Course Objectives
1. Develop hands-on skill in neural network architectures.
2. Master the fundamentals of optimization techniques.
3. Put AI Enablement techniques to work on real datasets and case studies.
4. Produce a reproducible, portfolio-ready project you can cite in a thesis, paper, or job application.
👥 Who Should Enroll?
• Master's and senior undergraduate students specializing in AI Enablement
• R&D engineers and working professionals applying AI Enablement in industry
• Academics and educators building research or teaching capacity in AI Enablement
• Data and computational scientists moving into neural network architectures
🚀 Key Learning Outcomes
• Confidence to implement neural network architectures in real projects.
• Confidence to reason about optimization techniques in real projects.
• A portfolio-grade AI Enablement deliverable you can defend and extend.
• A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
💎 What You'll Gain
Live & Recorded Sessions
Lifetime access to class recordingse-Certificate on Completion
Cryptographically verified credentialPost-Programme Support
Direct access to mentors & councilHands-On Experience
Notebooks, real-world code & datasetsCurriculum Outline
From Neuron to Network
• Perceptrons, activation functions and why non-linearity is essential
• Forward pass, loss functions and backpropagation mechanics
• Gradient descent variants and the role of the learning rate
Making Training Converge
• Initialisation, normalisation and vanishing or exploding gradients
• Regularisation: dropout, weight decay and early stopping
• Reading loss curves to diagnose what is going wrong
Convolutional Networks
• Convolution, pooling and receptive fields
• Standard architectures and residual connections
• Data augmentation and transfer learning from pretrained backbones
Recurrent and Attention Models
• Sequence modelling with RNNs and LSTMs, and their limitations
• Attention and the transformer block
• Tokenisation and embeddings for text
Building and Debugging Models
• PyTorch training loops, datasets and dataloaders
• GPU memory, batch size and mixed precision
• Overfitting a single batch as a first debugging step
Technical Specifications
| Parameter | Requirement |
|---|---|
| Covered Tool / Platform | Python |
| Covered Tool / Platform | PyTorch |
| Covered Tool / Platform | TensorFlow |
| Covered Tool / Platform | Keras |
| Covered Tool / Platform | CUDA |
| Covered Tool / Platform | Jupyter Notebook |
| Covered Tool / Platform | Weights & Biases |
Frequently Asked Questions
Scholar Feedback & Reviews
Based on 0 scholar submissions
Rating Breakdown
No verified reviews published yet. Be the first to share your academic experience.
Leave Scholar Feedback
Your rating will help prospective scholars. Ratings below 3 stars are routed privately to the faculty mentor for immediate response.
