Model Compression – Pruning, Quantisation and Knowledge Distillation
📋 KEY INSIGHTSModel compression reduces the size and computational cost of ML models — enabling deployment on edge devices, reducing inference latency and cost, and making large models practical...
Federated Learning – Privacy-Preserving Distributed Machine Learning
📋 KEY INSIGHTSFederated learning trains machine learning models across multiple devices or organisations without centralising the raw data — only model updates (gradients or weights) are shared. This enables...
Knowledge Graphs for Data Scientists – Graph Databases, Ontologies and Link Prediction
📋 KEY INSIGHTSA knowledge graph represents information as a network of entities (nodes) and relationships (edges) — (subject, predicate, object) triples such as (Albert_Einstein, bornIn, Ulm) or (Drug_X, inhibits,...
Conformal Prediction – Distribution-Free Uncertainty Quantification for Machine Learning
📋 KEY INSIGHTSConformal prediction is a framework for constructing prediction intervals that have a guaranteed coverage probability — if you request 90% coverage, the interval will contain the true...
Active Learning – Query Strategies, Annotation Efficiency and Sample-Efficient ML
📋 KEY INSIGHTSActive learning is the machine learning paradigm where the model selects which examples it wants to be labelled next, rather than learning from a passively collected, uniformly...
