🐍 Python
From zero to full-stack Python — practical, exam-oriented courses for every level
Beginner
10 hrs
Python Basics & Problem-Solving
Master syntax, conditions, and functions — no experience needed
Beginner
15 hrs
Python for Data Handling
Strings, files, and iterating over data with confidence
Intermediate
20 hrs
Python Data Structures
Lists, dictionaries, tuples, and regular expressions
Intermediate
15 hrs
Object-Oriented Programming in Python
Classes, inheritance, polymorphism, and encapsulation
Intermediate
25 hrs
Python for Web & Networking
Sockets, REST APIs, SQLite, and mini full-stack projects
Beginner
60 hrs
Full Python Application Programming
All five modules end-to-end — from basics to full-stack apps
🧠 AI & Neural Networks
ANN foundations through deep learning, competitive programming, and a full capstone project
Beginner
10 hrs
Introduction to Artificial Neural Networks
Biological neurons, perceptrons, and gradient descent — the foundation
Intermediate
12 hrs
Supervised Learning in Neural Networks
LMS, backpropagation, and MNIST digit classification
Intermediate
10 hrs
SVM and RBF Networks
Support Vector Machines, kernel methods, and function approximation
Intermediate
10 hrs
Attractor Networks & Associative Memory
Hopfield Networks, Boltzmann Machines, and TSP optimisation
Intermediate
10 hrs
Self-Organizing Maps & Unsupervised Learning
SOM, PCA, vector quantisation, and customer segmentation
Advanced
10 hrs
Advanced Topics: Deep Learning & RL
CNN, RNN/LSTM, reinforcement learning, and advanced optimisation
Advanced
8 hrs
Practical Applications of Neural Networks
Healthcare, finance, NLP, computer vision, and model deployment
All Levels
10 hrs
Exam Preparation & Problem-Solving Workshop
Mock tests, previous year papers, and interview question bank
Advanced
6 hrs
Neural Networks for Competitive Programming
Kaggle competitions, hackathons, and model speed optimisation
Advanced
12 hrs
Capstone: Build a Neural Network from Scratch
End-to-end: design, train, tune, and deploy — without libraries
∫ Complex Analysis
Complex functions, Cauchy-Riemann equations, conformal mappings, and contour integration
Intermediate
10 hrs
Introduction to Complex Analysis
Complex numbers, limits, continuity, and analytic functions
Intermediate
12 hrs
Cauchy-Riemann Equations & Analytic Functions
Verification, construction, and the Milne-Thompson method
Intermediate
8 hrs
Conformal Transformations
Standard mappings, bilinear transformations, and engineering uses
Intermediate
10 hrs
Complex Integration & Cauchy's Theorem
Line integrals, Cauchy's theorem, and the integral formula
📊 Probability & Statistics
Distributions, curve fitting, regression, and hypothesis testing — all exam-oriented
Intermediate
10 hrs
Probability Distributions — Discrete
Binomial and Poisson distributions with engineering applications
Intermediate
10 hrs
Probability Distributions — Continuous
Exponential, Normal distributions, and the Central Limit Theorem
Intermediate
8 hrs
Curve Fitting & Least Squares
Linear, parabolic, and power curve fitting from first principles
Intermediate
10 hrs
Correlation & Regression Analysis
Pearson's coefficient, rank correlation, and regression lines
Intermediate
8 hrs
Joint Probability Distributions
Joint PMF, marginal distributions, covariance, and independence
Intermediate
12 hrs
Sampling Theory & Hypothesis Testing
t-test, chi-square test, Type I/II errors, and A/B testing
Back to AI & Neural Networks
Advanced
12 Hours
Capstone: Build a Neural Network from Scratch
End-to-end — design, train, tune, and deploy without libraries
✓ Live group sessions (full course duration)
✓ Dedicated doubt-clearing within the batch
Pricing (per student)
10+ students
₹250 / hr
Total: ₹3,000
15+ students
₹200 / hr
Total: ₹2,400
20+ students
₹175 / hr
Total: ₹2,100
Prerequisites
- Completion of ANN Courses 1–9 (or equivalent)
- Strong Python programming skills
Overview
The capstone experience — students build a complete neural network from scratch in Python, without TensorFlow or PyTorch, and apply it to a real-world problem of their choosing. Ends with a project presentation and Q&A session.
Topics
| Hour | Topic | Details |
|---|---|---|
| 1 | Project Scoping | Define the problem, dataset, and success criteria. |
| 2 | Data Collection & Preprocessing | Collect and preprocess the project dataset. |
| 3 | Designing the Architecture | Design the neural network architecture from scratch. |
| 4 | Implementing Forward Propagation | Code the forward propagation step in pure Python. |
| 5 | Implementing Backpropagation | Code the backpropagation algorithm from scratch. |
| 6 | Training the Network | Train on the dataset, monitor loss and accuracy. |
| 7 | Evaluating Model Performance | Assess accuracy, precision, recall, and generalisation. |
| 8 | Hyperparameter Tuning | Optimise learning rate, batch size, and network depth. |
| 9 | Debugging & Improving | Identify and fix issues in the model pipeline. |
| 10 | Deploying the Model | Deploy the trained model for real-world use. |
| 11 | Presentation Preparation | Prepare a clear project summary and demo. |
| 12 | Project Demonstration & Q&A | Present the project and answer questions. |
Expected Outcomes
- Build a complete neural network from scratch in Python.
- Apply end-to-end ML workflow: data, design, train, tune, deploy.
- Present and explain the project confidently to an audience.