📚 Syllabus & Course Curriculum
Data Science & Analytics
Module-by-module breakdown of Advanced AI Techniques in Neural Information Processing, from foundations to a certified capstone project.
Architectures
• 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
Training
• Optimiser behaviour, learning-rate schedules and warmup
• Mixed precision, gradient accumulation and memory constraints
• Distributed training strategies and their communication costs
Representation
• Contrastive and masked-prediction objectives
• Fine-tuning, adapters and parameter-efficient methods such as LoRA
• Evaluating representation quality beyond downstream accuracy
Generative
• 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
Behaviour
• Probing, feature attribution and mechanistic interpretability approaches
• Adversarial robustness and distribution shift
• Calibration and uncertainty estimation in deep networks
Earn government-registered certification in Advanced AI Techniques in Neural Information Processing
e-Certificate and e-Marksheet issued on successful completion.
