Tag Archives: MachineLearning

From Transformers to AI Agents: Practical Roadmap to Modern Large Language Models (LLMs) – Faculty Development Program at Rashtriya Raksha University

June 26, 2026 Neil Harwani Leave a comment

From Transformers to AI Agents: Practical Roadmap to Modern Large Language Models (LLMs) – Notes from Faculty Development Program / Short Term Training Program (Generative AI – From Foundations to Frontiers) that I attended at Rashtriya Raksha University

Artificial Intelligence is evolving rapidly. What began with language prediction has now expanded into multimodal reasoning, autonomous agents, and enterprise AI systems. Understanding the complete ecosystem—not just ChatGPT—is becoming an essential skill for engineers, researchers, architects, and business leaders.

1. LLM Internals – How an LLM Actually Works

Data collection → cleaning → tokenization
Tokens converted into embeddings (dense vectors)
Positional encoding preserves sequence information
Transformer architecture using:
Next-token prediction using Softmax probabilities
Training via gradient descent and backpropagation
Inference through autoregressive generation

Key idea: LLMs do not memorize sentences—they learn statistical relationships among billions of tokens.

2. Mathematics Behind LLMs

Modern LLMs combine mathematics from multiple disciplines:

Linear Algebra (vectors, matrices, tensors)
Calculus (gradients, derivatives)
Probability & Statistics
Information Theory (Entropy, Cross-Entropy)
Optimization (Gradient Descent, Adam)
Graph Theory
Numerical Computing
High-dimensional Geometry

Core mathematical concepts

Embeddings
Attention mechanism
Softmax
Loss functions
Cosine similarity
Matrix multiplication
Eigenvectors & Singular Value Decomposition (SVD)

Mathematics remains the foundation behind every AI model.

3. Multimodal LLMs

Today’s AI models understand much more than text.

They can process:

Text
Images
Audio
Video
Documents (PDFs)
Tables
Source code
Structured enterprise data

Applications include:

Medical diagnostics
Autonomous vehicles
Satellite & GeoAI
Robotics
Scientific research
Digital assistants

4. Fine-Tuning

Organizations often adapt foundation models to their specific domains.

Popular approaches include:

Full Fine-Tuning
Parameter-Efficient Fine-Tuning (PEFT)
LoRA
QLoRA
Instruction Tuning
Reinforcement Learning from Human Feedback (RLHF)
Preference Optimization (e.g., DPO)

Fine-tuning helps models learn organizational knowledge, terminology, and task-specific behavior.

5. Enterprise Applications

LLMs are transforming almost every industry.

Examples include:

Customer support
Knowledge management
Software development
Healthcare
Finance
Manufacturing
Legal document analysis
Education
Cybersecurity
Scientific discovery
Government services
Geospatial intelligence (GeoAI)

6. Retrieval-Augmented Generation (RAG)

Instead of relying only on training knowledge, RAG retrieves relevant information before generating a response.

Typical pipeline: Documents → Chunking → Embeddings → Vector Database → Retrieval → Prompt Construction → LLM → Answer

Benefits:

More accurate responses
Reduced hallucinations
Access to current enterprise knowledge
Better explainability

7. Common RAG Patterns

Modern RAG systems use increasingly sophisticated architectures.

Examples include:

Naïve RAG
Semantic Search RAG
Hybrid Search (Keyword + Vector)
Parent–Child Retrieval
Multi-Vector Retrieval
Graph RAG
Knowledge Graph RAG
Agentic RAG
Corrective RAG (CRAG)
Self-RAG
Multi-hop RAG
Hierarchical RAG
Multimodal RAG

The trend is shifting from “search then answer” to intelligent reasoning over enterprise knowledge.

8. AI Agents

Unlike traditional chatbots, AI agents can plan, reason, and execute tasks.

Agent capabilities include:

Planning
Tool usage
Multi-step reasoning
Memory
Reflection
Self-correction
Collaboration with other agents

Common frameworks:

LangGraph
CrewAI
AutoGen
Semantic Kernel
OpenAI Agents SDK

Agents are moving AI from conversation to autonomous execution.

9. Model Context Protocol (MCP)

MCP is emerging as a standardized way for AI models to interact with external systems.

It enables models to securely connect with:

Databases
APIs
Git repositories
Local files
Enterprise applications
Business workflows
Development tools

Think of MCP as a “USB-C for AI,” providing a common interface between models and tools.

10. Ethics & Responsible AI

As AI capabilities expand, responsible development becomes increasingly important.

Key principles:

Fairness
Transparency
Explainability
Privacy
Security
Bias mitigation
Human oversight
Accountability
Regulatory compliance
Sustainability

Responsible AI is not optional—it is fundamental to building trustworthy systems.

Final Thoughts

The future of AI lies at the intersection of Transformers, Mathematics, Multimodal Intelligence, Fine-Tuning, RAG, AI Agents, MCP, and Responsible AI. Professionals who understand these interconnected concepts will be well-positioned to design the next generation of intelligent systems that are accurate, scalable, secure, and impactful.

The next wave of AI is not just about larger models—it is about smarter architectures, richer context, reliable reasoning, and responsible deployment.

Here is a curated list of technical keywords from the topics in this FDP & Article:

LLM Internals & Mathematics

Self-Attention Mechanism
Transformer Architecture
Positional Encoding (e.g., RoPE)
Softmax Function
Gradient Descent
Cross-Entropy Loss
Backpropagation
Stochastic Gradient Descent (SGD)
Backprop-through-time (BPTT)
Layer Normalization

Multi-Modal LLMs

Cross-Attention
Vision-Language Pre-training (VLP)
Contrastive Learning (e.g., CLIP)
Modality Alignment
Vector Quantization

Fine-Tuning

Parameter-Efficient Fine-Tuning (PEFT)
Low-Rank Adaptation (LoRA)
Quantized LoRA (QLoRA)
Reinforcement Learning from Human Feedback (RLHF)
Direct Preference Optimization (DPO)
Supervised Fine-Tuning (SFT)

Applications & RAG (Retrieval-Augmented Generation) Patterns

Vector Embeddings
Cosine Similarity
Approximate Nearest Neighbor (ANN)
Dense Retrieval
Hybrid Search (Lexical + Semantic)
Re-ranking Models (Cross-Encoders)
Context Window Constraints
Query Transformation

Agents & MCP (Model Context Protocol)

ReAct Framework (Reasoning and Acting)
Tool Calling / Function Calling
Autonomous Agents
Chain-of-Thought (CoT)
Model Context Protocol (MCP)
State Machine Routing

Ethics in AI

Algorithmic Bias
Differential Privacy
Alignment Problem
Data Provenance
Hallucination Mitigation
Toxicity Scoring

Thank you to all the speakers and staff at RRU.

#ArtificialIntelligence #GenerativeAI #LLM #MachineLearning #DataScience #RAG #AIAgents #MCP #ResponsibleAI #GeoAI #DeepLearning #Research #HigherEducation #EnterpriseAI #FutureOfWork

Concept Credit: Neil Harwani (Article) & Rashtriya Raksha University (FDP / Short term course)

Creation Help: ChatGPT, XMind and Gemini

📢 Stay informed:

Mathematics

Mathematics for Computer Science and Data Science – Sunday Mathematics: #2

June 20, 2026 Neil Harwani Leave a comment

Mathematics for Computer Science and Data Science

Why, What, Where, When and How These Concepts Matter

Post #1 on Sunday Mathematics here.

Data Science is much more than learning Python, SQL, or Machine Learning libraries. Mathematics provides the foundation that helps us understand why algorithms work, when to use them, and how to interpret results correctly. The following areas form the mathematical backbone of modern Data Science, AI, Computer Science, and GeoAI.

1. Linear Algebra – The Language of Data

Why?

Most datasets, images, videos, documents, and neural networks are represented as matrices and vectors.

What?

Vectors and matrices
Eigenvalues and eigenvectors
Matrix decompositions (SVD, QR, LU)
Dimensionality reduction (PCA)

Where?

Machine Learning
Deep Learning
Recommendation Systems
Computer Vision
Search Engines

Example

A photograph is simply a matrix of pixel values. PCA compresses large datasets while retaining important information.

2. Probability and Statistics – Managing Uncertainty

Why?

Real-world data is noisy and uncertain. Probability helps us quantify uncertainty and make informed decisions.

What?

Probability distributions
Bayes Theorem
Hypothesis testing
Confidence intervals
Regression models

Where?

Risk analysis
Medical diagnosis
Forecasting
Business analytics

Example

When Netflix recommends a movie, it predicts the probability that you will like it.

3. Calculus and Optimization – Learning from Data

Why?

Machine Learning models learn by minimizing errors.

What?

Derivatives and gradients
Partial derivatives
Gradient Descent
Convex optimization
Lagrange multipliers

Where?

Neural Networks
Deep Learning
Reinforcement Learning
Operations Research

Example

Training a neural network is like repeatedly walking downhill on an error landscape until the lowest error point is reached.

4. Discrete Mathematics – Logic of Computing

Why?

Computers work using logic, sets, graphs, and discrete structures rather than continuous mathematics.

What?

Mathematical logic
Set theory
Relations and functions
Graph theory
Combinatorics

Where?

Algorithms
Databases
Cybersecurity
Network analysis

Example

Social media friendship networks are graphs where people are nodes and relationships are edges.

5. Time Series Analysis – Understanding Change Over Time

Why?

Many datasets evolve with time.

What?

AR, MA, ARIMA models
Autocorrelation
Seasonality
Fourier Analysis
Spectral analysis

Where?

Stock markets
Weather forecasting
IoT sensors
Demand prediction

Example

Retail companies forecast future sales using historical sales patterns and seasonal trends.

6. Geospatial Mathematics – Understanding Location

Why?

Many decisions depend on “where” things happen.

What?

Coordinate systems
Map projections
Spatial interpolation
Spatial topology
Geodesic calculations

Where?

GPS systems
Urban planning
Agriculture
Disaster management
GeoAI

Example

Google Maps uses geospatial mathematics to determine shortest routes and travel times.

7. Category Theory – Mathematics of Abstraction

Why?

As systems become complex, we need higher-level ways to describe relationships and transformations.

What?

Objects and morphisms
Functors
Natural transformations
Monoids and monads

Where?

Functional programming
Distributed systems
Data pipelines
Advanced AI architectures

Example

Modern software frameworks use composable components that follow principles inspired by category theory.

How Everything Connects

A typical Data Science project uses all these areas:

Linear Algebra stores and transforms data.
Statistics helps understand uncertainty.
Calculus & Optimization train models.
Discrete Mathematics powers algorithms and data structures.
Time Series Analysis handles temporal data.
Geospatial Mathematics adds location intelligence.
Category Theory helps design scalable systems and abstractions.

Final Takeaway

Think of Data Science as building a smart city:

Linear Algebra = roads and infrastructure.
Statistics = traffic measurements and uncertainty.
Calculus = optimization of routes.
Discrete Mathematics = traffic rules and network design.
Time Series = predicting future traffic.
Geospatial Mathematics = maps and navigation.
Category Theory = the architectural blueprint connecting everything together.

Together, these mathematical foundations transform raw data into knowledge, predictions, decisions, and intelligent systems.

Brief, practical examples for each major category in the mind map, illustrating how these mathematical concepts are actually used in computer science and data science:

1. Discrete Mathematics

Mathematical Logic: Designing the conditional logic (if/else statements) in a software program or optimizing SQL queries.
Set Theory and Relations: Managing relational databases, where a database JOIN operation is directly based on the intersection of two sets.
Graph Theory: Social network analysis (e.g., how Facebook suggests friends) or GPS navigation apps finding the shortest route using Dijkstra’s algorithm.
Combinatorics: Calculating the number of possible password combinations to evaluate cybersecurity strength.

2. Calculus and Optimization

Differential Calculus: Gradient Descent in machine learning, which calculates gradients (derivatives) to update weights and minimize error during neural network training.
Integral Calculus: Computing the Area Under the ROC Curve (AUC) to measure the performance of a classification model.
Mathematical Optimization: Tuning a Support Vector Machine (SVM) classifier to find the optimal hyperplane that separates two classes with the maximum margin.

3. Linear Algebra

Vectors and Matrices: Representing an image as a matrix of pixel values so a computer can process it.
Eigenvalues and Eigenvectors: Google’s PageRank algorithm, which uses the dominant eigenvector of a web-link matrix to rank webpages in search results.
Matrix Decompositions: Singular Value Decomposition (SVD) used in Netflix-style recommendation systems to uncover latent user preferences.
Dimensionality Reduction: Principal Component Analysis (PCA), which shrinks a dataset with 100 features down to 3 key features to make it easier to visualize and train.

4. Probability and Statistics

Probability Theory: Naive Bayes Classifiers calculating the probability that an incoming email is “Spam” based on the words it contains.
Probability Distributions: Using a Poisson Distribution to model and predict the number of users logging into a server during peak hours.
Statistical Inference: Running an A/B Test on a website to see if a blue button yields a statistically significant increase in clicks compared to a red button.
Regression Analysis: Using Logistic Regression to predict a binary outcome, such as whether a bank customer will default on a loan (Yes/No).

5. Geospatial Mathematics

Coordinate Systems and Projections: Converting raw GPS latitude and longitude coordinates into a flat, 2D map projection in Google Maps.
Spherical Geometry: Using the Haversine formula to calculate the actual flight path distance between London and New York over the Earth’s curved surface.
Spatial Analysis and Interpolation: Kriging to estimate pollution levels at an unmeasured city block based on data from surrounding air-quality sensors.
Topology and Spatial Relations: Defining geofences, such as an app triggering a notification when a delivery driver enters a 1-mile radius buffer around your house.

6. Category Theory

Fundamental Structures: Ensuring function composition in code is associative (e.g., making sure f(g(x)) behaves reliably in functional programming languages like Haskell or Scala).
Functors and Transformations: Using a .map() function in JavaScript or Python to transform every element inside a list without altering the list’s overall structure.
Monads and Monoids: Using a Monad to safely handle “Null” values or side effects (like API calls) without crashing a program or using Monoids in big data frameworks (like MapReduce) to parallelize data aggregation.

7. Time Series Analysis

Stochastic Processes: Modeling stock price movements as a Random Walk to simulate future market risks.
Time Series Modeling: An ARIMA model predicting next month’s electricity demand based on historical usage patterns over the last 5 years.
Frequency Domain Analysis: Using Fourier Transforms to clean audio data by converting the sound wave into frequencies and filtering out background hiss/noise.
Evaluation and Decomposition: Splitting retail sales data into its baseline trend, seasonal holiday spikes, and random noise to understand true business growth.

Concept Credit: Neil Harwani

Creation Help: ChatGPT, XMind and Gemini

📢 Stay informed:

AIML, Generative AI, GraphML

🚕 From Traffic Prediction to Decision Intelligence — A Graph ML Story

May 1, 2026 Neil Harwani Leave a comment

Below are insights from my open book assignment / exam at IIT GNX converted into a blog-based story with help on AI/GenAI. This was the most exciting open book assignment / exam given by me till now. Open to comments, suggestions, ideas, debates, improvements, corrections, reviews, etc. Feel free to email me (refer contact detail in the bottom of this article) or message me on LinkedIn.

📌 The Real Question Isn’t Prediction — It’s Decision

Most data science projects stop at:

“Model accuracy improved.”

But in real systems—especially ride-hailing, logistics, BFSI, or infra platforms—that’s not enough.

The real question is:

What decision becomes better because of this model?

This assignment pushed me to think differently.

Instead of just predicting traffic, I asked:

How can traffic forecasts drive real operational decisions in a ride-hailing system?

🧠 Problem Framing (What Actually Matters)

We used the METR-LA dataset:

207 traffic sensors
5-minute interval readings
~4 months of data
Objective: predict traffic speeds 5, 15, 30 minutes ahead

But here’s the twist:

👉 Each sensor is not independent 👉 Roads are connected systems 👉 Congestion spreads like a graph

So instead of treating data as rows in a table…

We treat it as a graph system

🌐 Thinking in Graphs (Systems Thinking)

Nodes → Traffic sensors
Edges → Road proximity / connectivity
Signals → Speed over time

This is where complex systems + spatial thinking come into play.

Traffic ≠ isolated events Traffic = propagating behavior across a network

📊 What the Data Told Us

From exploratory analysis:

Congestion appears in clusters (not random points)
Patterns repeat during commute peaks
Slowdowns are both: Temporal (time-based) Spatial (location-based)

👉 This is critical insight for operations:

Time tells you when to act
Space tells you where to act

🤖 Models We Tested (Keep It Honest)

To make this real (not overhyped), we compared:

1. Persistence Model

“Tomorrow ≈ Today”
Surprisingly strong for 5-minute prediction

2. Random Forest

Uses past lag features
Captures non-linear temporal patterns

3. Graph ML Model (GConvGRU)

Combines: Graph Convolution → spatial relationships GRU → temporal dynamics

📈 Results (Where Graph ML Actually Matters)

From the results:

Horizon Best Insight (Labels)

5 min Simple models work well

15 min Graph ML starts winning

30 min Graph ML clearly better

👉 Why?

Because:

Short-term = inertia Medium-term = propagation

Graph models capture how congestion spreads, not just how it exists.

🚕 Turning Predictions into Decisions

This is where the project becomes real.

🔴 If congestion is predicted in next 15–30 mins:

Reduce driver inflow into that corridor
Increase ETA buffers
Trigger incentives in nearby zones

🟢 What this enables:

Better ETA reliability
Smarter driver utilization
Reduced customer wait time
Proactive—not reactive—operations

🧩 The Big Shift: Model → Decision System

This project is NOT just:

“Train model → predict → done”

It is:

EDA → Model → Evaluation → Business Rules → Decision Intelligence

The work is framed as a decision-intelligence exercise rather than only model-building

⚠️ Reality Check (Limitations)

Let’s stay grounded.

The dataset does NOT include:

Ride demand
Driver availability
Weather
Events
Airport queues

So:

This is traffic intelligence, not full business optimization

🔧 What I Learned (Real Engineering Insights)

From my own notes:

Training time is real (hours, not minutes)
GPU/TPU selection matters
Early stopping is critical (overfitting is silent killer)
Graph ML pipelines are non-trivial systems
LLMs can accelerate development—but thinking is still yours

🏗️ Architecture Thinking (My Take)

What excites me most is not the model.

It’s the system design potential:

Imagine combining this with:

Real-time driver GPS
Demand prediction models
Event/weather APIs
Reinforcement learning for dispatch

👉 You get:

Autonomous Decision Systems for Urban Mobility

🔮 Where This Connects to My Larger Work

This directly aligns with what I’m exploring:

Agentic AI + Graph Systems + Probabilistic Models for Autonomous Debugging & Decision Systems

Traffic is just one domain.

Same thinking applies to:

Microservices failures
Network congestion
Financial risk propagation
Supply chain disruptions

🧠 Final Thought

A staff engineer once asked:

“What gets harder after this lands?”

For me, this project answered a deeper question:

What gets smarter after this lands?

📌 Bottom Line

Graph ML is not just “better ML”
It is better system understanding
Real value comes when: Predictions → Decisions Models → Actions Data → Intelligence

📢 Stay informed:

#GraphML #DataScience #AI #SpatialDataScience #RideHailing #DecisionIntelligence #SystemsThinking #GNN #MachineLearning #TechLeadership

Machine Learning

Learnings from assignments / open book exams at Indian Institute of Technology Gandhinagar – Executive Masters in Data Science for Decision Making

April 30, 2026 Neil Harwani Leave a comment

One important lesson I learned while working with spatio-temporal graph data on the METR-LA dataset during my Executive Masters open-book assignment:

Do not keep switching between Claude, ChatGPT, Perplexity, Gemini, and other LLMs or AI tools during the execution stage. This lesson has repeated itself in the two years throughout the Executive Masters whenever we have been allowed to use LLMs.

My learning:

• Different LLMs reason differently

• They are trained and fine-tuned differently

• They suggest different libraries, assumptions, fixes, and coding styles

• Mixing their guidance during debugging can create unnecessary chaos

• What looks like “more intelligence” can become “more confusion”

• Multi-model thinking is useful during brainstorming

• It helps in debating, exploring, comparing, and expanding ideas

• But once execution begins, consistency matters more than variety

• Pick one model and work through the problem step by step

• Ask it to explain, debug, simplify, correct, and iterate

• Stay with one reasoning path until the solution stabilizes

My conclusion:

Use multiple LLMs for exploration.

Use one LLM for execution.

Mixing models during ideation can create insight.

Mixing models during implementation can create chaos.

This is especially true in technical work involving data science, graph ML, spatio-temporal modeling, package dependencies, tensor shapes, runtime environments, and debugging.

Progress comes from disciplined iteration, not tool-hopping.

Note: Enhanced / compiled with help of AI / LLMs

AIML, Generative AI

Dimensions for Artificial Intelligence / GenAI / LLMs / Deep Learning / Neural Networks / Data Science to ponder on – Part 1-Assisted by AI – ChatGPT

April 17, 2026 Neil Harwani Leave a comment

🧠 1. Model Performance & Quality

Beyond accuracy:

Precision / Recall / F1-score
ROC-AUC
Calibration (probability correctness)
Generalization ability
Robustness (noise, adversarial inputs)
Stability (variance across runs)
Overfitting / Underfitting control
Latency (response time)
Throughput (requests per second)

⚖️ 2. Responsible AI / Ethics

Along with fairness, bias, explainability, interpretability:

Accountability
Transparency
Non-discrimination
Inclusiveness
Human oversight / Human-in-the-loop
Ethical alignment
Value alignment (especially for LLMs)
Safety (harm prevention)

🔐 3. Security & Privacy

Critical for enterprise and GenAI:

Data privacy (PII protection)
Differential privacy
Federated learning capability
Model security (model theft, extraction)
Prompt injection resistance (LLMs)
Data leakage prevention
Adversarial robustness
Access control & authentication

📊 4. Data Quality & Governance

Often more important than model itself:

Data completeness
Data consistency
Data lineage
Data drift detection
Concept drift detection
Bias in training data
Data freshness
Label quality
Auditability

⚙️ 5. Model Lifecycle & MLOps

Operational excellence:

Reproducibility
Versioning (data + model)
Monitoring (real-time + batch)
Model retraining strategy
Deployment reliability
Rollback capability
CI/CD for ML pipelines
Observability (logs, metrics, traces)

🧩 6. LLM / GenAI Specific Parameters

Very important for your GenAI work:

Hallucination rate
Faithfulness (groundedness to source)
Context retention (long context handling)
Instruction following
Toxicity / harmful output control
Prompt sensitivity
Response consistency
Token efficiency (cost optimization)
Alignment with system prompts / policies
Retrieval quality (RAG precision/recall)

🧪 7. Evaluation & Testing

For enterprise-grade systems:

Benchmarking (standard datasets)
Stress testing
Edge case coverage
Scenario testing
A/B testing
Human evaluation (subjective scoring)
Red teaming (especially for GenAI)

🌐 8. Business & Product Metrics

Often ignored in technical discussions:

ROI / Cost-benefit
User satisfaction
Adoption rate
Time saved / productivity gain
Decision impact quality
Revenue impact
Risk reduction

🧭 9. Governance & Compliance

Especially relevant in India (DPDP Act etc.):

Regulatory compliance
Audit trails
Model documentation (Model Cards)
Explainability for regulators
Consent management
Data residency

🧠 Quick Memory Framework

You can compress everything into:

👉 FAPES-DLMGB

Fairness & Ethics
Accuracy & Performance
Privacy & Security
Explainability
Scalability & Stability
Data Quality
Lifecycle (MLOps)
Monitoring
Governance
Business Impact

Reference frameworks:

NIST AI Risk Management Framework
ISO/IEC 42001

Note: Enhanced / compiled with help of AI / LLMs

1. LLM Internals – How an LLM Actually Works

2. Mathematics Behind LLMs

3. Multimodal LLMs

4. Fine-Tuning

5. Enterprise Applications

6. Retrieval-Augmented Generation (RAG)

7. Common RAG Patterns

8. AI Agents

9. Model Context Protocol (MCP)

10. Ethics & Responsible AI

Final Thoughts

LLM Internals & Mathematics

Multi-Modal LLMs

Fine-Tuning

Applications & RAG (Retrieval-Augmented Generation) Patterns

Agents & MCP (Model Context Protocol)

Ethics in AI

Share this:

Like this:

Mathematics for Computer Science and Data Science

Why, What, Where, When and How These Concepts Matter

1. Linear Algebra – The Language of Data

Why?

What?

Where?

Example

2. Probability and Statistics – Managing Uncertainty

Why?

What?

Where?

Example

3. Calculus and Optimization – Learning from Data

Why?

What?

Where?

Example

4. Discrete Mathematics – Logic of Computing

Why?

What?

Where?

Example

5. Time Series Analysis – Understanding Change Over Time

Why?

What?

Where?

Example

6. Geospatial Mathematics – Understanding Location

Why?

What?

Where?

Example

7. Category Theory – Mathematics of Abstraction

Why?

What?

Where?

Example

How Everything Connects

Final Takeaway

1. Discrete Mathematics

2. Calculus and Optimization

3. Linear Algebra

4. Probability and Statistics

5. Geospatial Mathematics

6. Category Theory

7. Time Series Analysis

Share this:

Like this:

📌 The Real Question Isn’t Prediction — It’s Decision

🧠 Problem Framing (What Actually Matters)

🌐 Thinking in Graphs (Systems Thinking)

📊 What the Data Told Us

🤖 Models We Tested (Keep It Honest)

1. Persistence Model

2. Random Forest

3. Graph ML Model (GConvGRU)

📈 Results (Where Graph ML Actually Matters)

🚕 Turning Predictions into Decisions

🔴 If congestion is predicted in next 15–30 mins:

🟢 What this enables:

🧩 The Big Shift: Model → Decision System