Neural Networks

Neural Networks #

• A network of artificial neurons inspired by how neurons function in the human brain.
• At its core - a mathematical model designed to process and learn from data.
• Neural networks form the foundation of Deep Learning (involves training large and complex networks on vast amounts of data).

flowchart LR
 subgraph subGraph0["Input Layer"]
        I1(("Input 1"))
        I2(("Input 2"))
        I3(("Input 3"))
  end
 subgraph subGraph1["Hidden Layer"]
        H1(("Hidden 1"))
        H2(("Hidden 2"))
        H3(("Hidden 3"))
  end
 subgraph subGraph2["Output Layer"]
        O(("Output"))
  end
    I1 --> H1 & H2 & H3
    I2 --> H1 & H2 & H3
    I3 --> H1 & H2 & H3
    H1 --> O
    H2 --> O
    H3 --> O

    style I1 fill:#C8E6C9
    style I2 fill:#C8E6C9
    style I3 fill:#C8E6C9
    style H1 stroke:#2962FF,fill:#BBDEFB
    style H2 fill:#BBDEFB
    style H3 fill:#BBDEFB
    style O fill:#FFCDD2
    style subGraph0 stroke:none,fill:transparent
    style subGraph1 stroke:none,fill:transparent
    style subGraph2 stroke:none,fill:transparent

Structure of a Neural Network #

A typical neural network has three main layers:

Conditional Probability & Bayes’ Theorem

March 12, 2026

Conditional Probability & Bayes’ Theorem #

Probability often changes when we learn new information.

Conditional probability and Bayes’ theorem give a structured way to update beliefs using evidence.

Conditional probability updates probabilities after observing an event.

Bayes’ theorem lets you estimate a hidden cause from observed evidence.

Naïve Bayes turns Bayes’ theorem into a practical classifier by assuming conditional independence of features given the class.

flowchart TD

A[Conditional<br/>probability] -->|foundation| B[Bayes<br/>theorem]
D[Independent<br/>events] -->|implies| C[Independence]
C -->|simplifies| A

E[Prior] -->|with likelihood| B
F[Likelihood] -->|updates| H[Posterior]
G[Evidence] -->|normalises| B
B -->|yields| H

I[Naïve<br/>Bayes] -->|uses| B
J[Naïve<br/>assumption] -->|assumes| C
K[Features] -->|given class| J
L[Class] -->|conditions| J
I -->|predicts| M[Classification]
M -->|selects| L

style A fill:#90CAF9,stroke:#1E88E5,color:#000
style B fill:#90CAF9,stroke:#1E88E5,color:#000
style C fill:#90CAF9,stroke:#1E88E5,color:#000

style D fill:#CE93D8,stroke:#8E24AA,color:#000
style E fill:#CE93D8,stroke:#8E24AA,color:#000
style F fill:#CE93D8,stroke:#8E24AA,color:#000
style G fill:#CE93D8,stroke:#8E24AA,color:#000
style J fill:#CE93D8,stroke:#8E24AA,color:#000
style K fill:#CE93D8,stroke:#8E24AA,color:#000
style L fill:#CE93D8,stroke:#8E24AA,color:#000

style H fill:#C8E6C9,stroke:#2E7D32,color:#000
style I fill:#C8E6C9,stroke:#2E7D32,color:#000
style M fill:#C8E6C9,stroke:#2E7D32,color:#000

Quick summary #

• Conditional probability: updates probability after an event is known.
• Multiplication rule: computes joint probability from conditional parts.
• Independence: tested using \( P(A\cap B)=P(A)P(B) \) .
• Total probability: breaks a probability into weighted cases.
• Bayes’ theorem: reverses conditioning to infer causes from evidence.

What’s next #

Probability Distributions
Move from events to random variables and distributions.

Machine Learning

August 6, 2024

Machine Learning #

stateDiagram-v2

    %% ===== CLASS DEFINITIONS (Math-based colours) =====
    classDef algebra fill:#cfe8ff,stroke:#1e3a8a,stroke-width:1px
    classDef probability fill:#d1fae5,stroke:#065f46,stroke-width:1px
    classDef geometry fill:#ffedd5,stroke:#9a3412,stroke-width:1px
    classDef logic fill:#ede9fe,stroke:#5b21b6,stroke-width:1px
    classDef category font-style:italic,font-weight:bold,fill:#aaaaaa,stroke:#374151,stroke-width:3px

    %% ===== ROOT =====
    ML: Machine Learning

    %% ===== SUPERVISED =====
    ML --> SL:::category
    SL: Supervised Learning

    SL --> Regression
    Regression --> LR:::algebra
    LR: Linear Regression

    LR --> NN:::algebra
    NN: Neural Network

    NN --> DT:::logic
    DT: Decision Tree

    SL --> Classification
    Classification --> NB:::probability
    NB: Naive Bayes

    NB --> KNN:::geometry
    KNN: k-Nearest Neighbours

    KNN --> SVM:::algebra
    SVM: Support Vector Machine
    
    %% ===== UNSUPERVISED =====
    ML --> USL:::category
    USL: Unsupervised Learning

    USL --> Clustering
    Clustering --> KM:::geometry
    KM: K-Means

    KM --> GMM:::probability
    GMM: Gaussian Mixture Model

    GMM --> HMM:::probability
    HMM: Hidden Markov Model

    %% ===== REINFORCEMENT =====
    ML --> RL:::category
    RL: Reinforcement Learning

    RL --> DM:::logic
    DM: Decision Making

AI Stack

AI Stack #

The AI Stack describes the layers required to build an end-to-end AI system, from infrastructure at the bottom to user-facing applications at the top.

Different organisations represent the AI stack differently; this is a simplified conceptual view for learning.

Each layer depends on the one below it.

graph TB

    subgraph APP["Applications"]
        A[User Interfaces & Integrations]
    end

    subgraph ORCH["Orchestration"]
        O[Workflows • Agents • Control Logic]
    end

    subgraph DATA["Data"]
        D[Data Sources • Pipelines • Vector DBs]
    end

    subgraph MODEL["Models"]
        M[ML • DL • Foundation Models • LLMs]
    end

    subgraph INFRA["Infrastructure"]
        I[Cloud • On-prem • GPUs • Storage]
    end

    %% Styling
    style APP fill:#FFCCBC
    style ORCH fill:#90CAF9
    style DATA fill:#BBDEFB
    style MODEL fill:#C8E6C9
    style INFRA fill:#E1F5FE

    style A fill:#FFE0B2
    style O fill:#B3E5FC
    style D fill:#E3F2FD
    style M fill:#DCEDC8
    style I fill:#E1F5FE

1. Infrastructure #

The foundation that provides compute and storage.

Artificial Neuron and Perceptron

Artificial Neuron and Perceptron #

knowledge in neural networks is stored in connection weights, and learning means modifying those weights.

Biological Neuron #

A biological neuron is a specialised cell that processes and transmits information through electrical and chemical signals.

Core components:

• Dendrites: receive signals from other neurons
• Cell body (soma): processes incoming signals
• Axon: transmits the output signal
• Synapses: connection points between neurons

Biological intuition:

• many inputs arrive to one neuron
• one neuron can connect out to many neurons
• massive parallelism enables fast perception and recognition

Artificial Neuron #

An artificial neuron is a simplified computational model inspired by biological neurons.

ML Workflow

Machine learning Workflow #

Data is the foundation of any machine learning system. Quality of data matters more than model complexity.

Role of Data #

Data determines:

• What patterns the model can learn
• How well it generalises
• Whether bias or noise is introduced

Bad data → bad model (even with perfect algorithms).

Data Preprocessing, wrangling #

Raw data is never ready for training.

Data Issues

• Noise
  • For objects, noise is an extraneous object
  • For attributes, noise refers to modification of original values
  • Use Log or Z Transfer to convert to mean
• Outliers
  • Data objects with characteristics that are considerably different than most of the other data objects in the data set
  • Handle: Use IQR method
  • Find Lower and Upper Bound and replace Outlier with Lower or Upper Bound
• Missing Values
  • Eliminate data objects or variables
  • Handle: Estimate missing values
    • Mean, Median or Mode
    • Prefer Median if there are missing outliers
  • Ignore the missing value during analysis
• Duplicate Data
  • Major issue when merging data from heterogeneous sources
• Inconsistent Codes
  • Find all Unique and transfer all inconsistent to

Data Preprocessing techniques

Conditional Probability

March 12, 2026

Conditional Probability #

Conditional probability updates the probability of an event when new information is available.

It shows up whenever a question says:

• “given that…”
• “among those who…”
• “out of the items that…”
• “if it does not fail immediately…”

Key takeaway: Conditional probability is always:

joint probability ÷ probability of the condition.

The condition must not be an impossible event.

Prior vs posterior #

• Prior probability: probability with no condition (before new information)

Bayes’ Theorem

Bayes’ Theorem #

2.1 Total probability (needed for Bayes) #

Often we split the world into cases \( E_1,E_2,\dots,E_k \) that:

• are mutually exclusive
• cover the whole sample space

Then for any event \( A \) :

Tree intuition:

Naïve Bayes

March 12, 2026

Naïve Bayes #

Naïve Bayes is a probabilistic classifier.

• Supervised Learning Problem
• Binary Classification - final target variable is considered in two classes
• Hypothesis is target which you want to classify
• Total Probability (Prior) of Yes and No is already calculated
• Post / Posterior is when you start studying data
• Based on max probability of hypotheses classify given instance into a class

It predicts a class label by computing:

Probability Distributions

February 22, 2026

Probability Distributions #

Probability distributions are the bridge between: real-world randomness and mathematical modelling.

A random experiment produces outcomes. A random variable turns those outcomes into numbers. A probability distribution tells you how likely each number (or range of numbers) is.

Key takeaway: A distribution is a complete “story” about uncertainty: what values are possible, how likely they are, and how we summarise them (mean, variance).

flowchart TD
	PD["Probability<br/>distributions"] --> RV["Random<br/>variables"]
	PD["Probability<br/>distributions"] --> DS["Common<br/>distributions"]

	style PD fill:#90CAF9,stroke:#1E88E5,color:#000
	style RV fill:#90CAF9,stroke:#1E88E5,color:#000
	style DS fill:#90CAF9,stroke:#1E88E5,color:#000

AI/ML Connection #

• Many ML models are probabilistic: they assume data (or errors) follow a distribution.
• Loss functions often come from distribution assumptions: squared loss aligns with Gaussian noise.
• Naïve Bayes (from the previous module) becomes practical once you can model: \( P(X\mid Y) \) using suitable distributions.

In practice: choosing a distribution is a modelling decision. It affects: prediction, uncertainty estimates, and what “rare” or “typical” means in your data.