Convolutional Neural Networks (CNNs) are specialised neural networks designed for data with spatial structure, especially images. They became the standard model for computer vision because they preserve spatial locality, reuse the same pattern detector across the image, and build representations hierarchically. In practical terms, a CNN starts by learning simple features such as edges and corners, then combines them into textures, shapes, object parts, and finally full semantic categories.
Scale-out frameworks distribute data and computation across networked machines. Their value comes from aggregate compute and storage, while their main costs are communication, scheduling, serialisation, and repeated synchronisation.
Course coverage:
Cluster computing with Hadoop and Spark
MapReduce k-means, mini-batch and streaming variants
Convergence and communication reduction
Distributed convolutional neural networks: data and model parallelism
Layer or tensor slicing, mixed precision, pipelining, and distributed execution frameworks
Population-based search explores with many candidate solutions at once. Genetic Algorithms evolve encoded solutions, Ant Colony Optimisation builds paths using collective pheromone signals, and neuroevolution applies evolutionary ideas to neural-network design.
Genetic Algorithm
Ant Colony Optimisation
Neural Architecture Search
Use case : Neuro Evolution - Evolutionary computation to design or train neural networks
flowchart TD
P["Population-based search"] --> G["Genetic Algorithms"]
P --> A["Ant Colony Optimisation"]
G --> N["Neuroevolution"]
N --> D["Deep network design"]
style P fill:#E1F5FE
style G fill:#C8E6C9
style A fill:#FFF9C4
style N fill:#EDE7F6
style D fill:#C8E6C9
Instance-based learning is a family of methods that do not build one explicit global model during training. Instead, they store training examples and delay most of the work until a new query arrives.
When a new point must be classified or predicted, the algorithm compares it with previously seen examples, finds the most relevant neighbours, and uses them to produce the answer.
Instance-based Learning covers three linked ideas:
Part-of-Speech tagging assigns a grammatical category to each word in a sequence. Because many words can play different grammatical roles, a tagger must use surrounding context rather than examine each word independently.
flowchart TD
A["Word Sequence"] --> B["Use Context"]
B --> C["Infer Hidden Tags"]
C --> D["Tagged Sequence"]
style A fill:#E1F5FE
style B fill:#C8E6C9
style C fill:#FFF9C4
style D fill:#EDE7F6
Temporal-Difference (TD) learning updates predictions from one transition at a time. It learns directly from experience like Monte Carlo methods, but it does not need to wait until the episode ends.
Course Content covered in this module:
Temporal-Difference Learning
TD(0), SARSA, Q-Learning and Expected SARSA
TD learning updates an estimate using an immediate reward and another current estimate.
Once the basic ideas of convolution, pooling, channels, and classifier heads are understood, the next step is to study how successful CNN architectures are designed in practice. The history of deep CNNs is not just a list of famous models. It is a progression of design ideas: smaller filters, more depth, better optimisation, bottlenecks, multi-scale processing, residual connections, and transfer learning.
Key takeaway: Deep CNN architectures evolved by solving specific problems one by one: LeNet established the template, AlexNet proved deep learning could dominate large-scale vision, VGG simplified the design, NiN introduced powerful 1 × 1 ideas, GoogLeNet made multi-scale processing efficient, and ResNet solved the optimisation problem of very deep networks.
April 19, 2026