Programme Parameters
Advanced Postgrad
3 Days (4.5 Hrs)
Online (e-LMS)
• Prior working knowledge of the field and comfort with core tools and quantitative reasoning.
• A laptop or desktop with a stable internet connection.
• Willingness to complete assignments and the capstone project.
About This Course
This course is designed to cover the latest advancements in AI techniques presented at the Neural Information Processing Systems (NeurIPS) Conference. Every participant receives a verified e-Certificate and e-Marksheet from the Deep Science & Technology Consortium.
🎯 Program Aim
This course is designed to cover the latest advancements in AI techniques presented at the Neural Information Processing Systems (NeurIPS) Conference.
📋 Course Objectives
1. Put AI Enablement techniques to work on real datasets and case studies.
2. Build a defensible project you can showcase to supervisors, reviewers, or employers.
👥 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
🚀 Key Learning Outcomes
• A demonstrable AI Enablement project for your research or industry portfolio.
• 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
Beyond the Standard Feedforward Model
• Attention and transformer internals, including positional encoding choices
• Normalisation, residual connections and why deep networks train at all
• State-space and recurrent alternatives for long sequences
Optimisation at Scale
• Optimiser behaviour, learning-rate schedules and warmup
• Mixed precision, gradient accumulation and memory constraints
• Distributed training strategies and their communication costs
Self-Supervision and Transfer
• Contrastive and masked-prediction objectives
• Fine-tuning, adapters and parameter-efficient methods such as LoRA
• Evaluating representation quality beyond downstream accuracy
Modern Generative Formulations
• Diffusion and flow-based models: training and sampling trade-offs
• Autoregressive generation, decoding strategies and their artefacts
• Evaluation of generative output where no single metric suffices
Interpretability and Robustness
• Probing, feature attribution and mechanistic interpretability approaches
• Adversarial robustness and distribution shift
• Calibration and uncertainty estimation in deep networks
Technical Specifications
| Parameter | Requirement |
|---|---|
| Covered Tool / Platform | Python |
| Covered Tool / Platform | TensorFlow |
| Covered Tool / Platform | PyTorch |
| Covered Tool / Platform | Keras |
| Covered Tool / Platform | Scikit-learn |
| Covered Tool / Platform | Jupyter Notebook |
| Covered Tool / Platform | Google Colab |
| Covered Tool / Platform | Hugging Face |
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.
