Year 2 C.S, B.F, M.L, MATH

Year 2 is where you transition from:

“Strong learner” → “Emerging engineer.”

Year 1 gave you foundations.
Year 2 builds depth, rigor, and real engineering maturity.

Goal of Year 2:

• Advanced data structures mastery
• Serious probability & linear algebra comfort
• Strong applied ML capability
• Internship-level readiness
• 6–8 substantial projects

YEAR 2 — Month-by-Month Plan

Structure per month:

• CS Focus
• Math Focus
• ML Focus
• Project Milestone

MONTH 1 — Advanced Trees & Graph Foundations

CS

• Balanced trees (AVL, Red-Black — concept level)
• Heaps (deep)
• Priority queues
• Advanced graph representations
• Complexity comparisons

Math

• Linear algebra review
• Vector spaces
• Linear independence
• Basis & dimension (intuition)

ML

• Review gradient descent mathematically
• Loss surface visualization
• Optimization intuition

Project

Build:

• Priority-based job scheduler
• Graph traversal visualizer (BFS, DFS, Dijkstra)

Goal:
Think in terms of trade-offs and performance.

MONTH 2 — Graph Algorithms & Optimization

CS

• Dijkstra (deep)
• Bellman-Ford
• Topological sorting
• Minimum spanning trees (Kruskal, Prim)

Math

• Eigenvalues & eigenvectors (calculation + intuition)
• Why eigenvalues matter in ML

ML

• PCA (Principal Component Analysis)
• Dimensionality reduction
• Implement PCA from scratch

Project

Build:

• Pathfinding simulator
• PCA visualization tool

Goal:
Connect linear algebra to ML practically.

MONTH 3 — Databases & Data Systems

CS

• Advanced SQL
• Indexing
• Query optimization basics
• Transactions & ACID
• Intro to NoSQL (conceptual)

Math

• Probability distributions:
  • Normal
  • Binomial
  • Poisson

ML

• Naive Bayes
• Probabilistic modeling
• Generative vs discriminative models

Project

Build:

• ML system backed by database
• Naive Bayes spam classifier

Goal:
Understand data pipelines seriously.

MONTH 4 — Object-Oriented & Clean Architecture

CS

• Advanced OOP
• Design patterns (intro level)
• SOLID principles
• Modular architecture
• Testing (unit tests)

Math

• Conditional probability deeply
• Bayes theorem applications

ML

• Decision trees (mathematics behind splits)
• Random forest deeply
• Overfitting analysis

Project

Build:

• Modular ML framework
• Compare decision tree vs random forest

Goal:
Engineer-quality code, not scripts.

MONTH 5 — Systems Thinking

CS

• Intro to Operating Systems:
  • Processes vs threads
  • Memory basics
  • Scheduling
• Intro to concurrency concepts

Math

• Expectation
• Variance
• Covariance
• Correlation

ML

• Linear models with regularization (L1, L2)
• Bias-variance tradeoff deeply

Project

Build:

• Model comparison dashboard
• Evaluate regularization effects visually

Goal:
Think about computation limits.

MONTH 6 — Mid-Year Major Project

Integration month.

Project:

Build a Full ML Pipeline System:

1. Data ingestion
2. Cleaning
3. Feature engineering
4. Model selection
5. Hyperparameter tuning
6. Evaluation
7. Persistence (save model)

Example ideas (Uganda context):

• Crop yield prediction
• Student performance predictor
• Business sales forecasting

Checkpoint:
You should be comfortable:

• Explaining PCA
• Explaining bias-variance tradeoff
• Implementing graph algorithms
• Designing clean architecture

MONTH 7 — Advanced Algorithms

CS

• Dynamic programming (intro)
• Memoization
• Greedy algorithms
• Complexity comparisons

Math

• Multivariable calculus intro:
  • Partial derivatives
  • Gradient intuition

ML

• Gradient descent mathematically
• Stochastic vs batch gradient descent

Project

Build:

• Dynamic programming problems solver
• Gradient descent visualizer

Goal:
Optimization becomes intuitive.

MONTH 8 — ML Depth

CS

• Code optimization
• Profiling performance
• Memory efficiency

Math

• Chain rule (important for backprop later)
• Optimization intuition

ML

• Support Vector Machines
• Margin intuition
• Kernel trick concept

Project

Implement:

• SVM from scratch (simplified)
• Compare SVM vs logistic regression

Goal:
Prepare for neural networks later.

MONTH 9 — Data Engineering Basics

CS

• Data pipelines
• ETL concepts
• Intro to distributed thinking (conceptual only)

Math

• Review & strengthen weak topics

ML

• Feature scaling deeply
• Model tuning strategies
• Cross-validation strategies

Project

Build:

• Automated ML experimentation system

Goal:
Engineer mindset over notebook mindset.

MONTH 10 — Model Deployment & APIs

CS

• API development (Flask or FastAPI)
• Serialization (pickle/joblib)
• REST fundamentals

Math

• Consolidation

ML

• Model monitoring basics
• Evaluation under real conditions

Project

Deploy ML model as API
(Optional: simple web interface)

Goal:
Move toward production thinking.

MONTH 11 — System Design for ML

CS

• High-level system design:
  • Load balancing
  • Caching basics
  • Scalability thinking

Math

• Advanced probability review

ML

• Ensemble methods deeply
• Model comparison strategies

Project

Design:

• Scalable ML service architecture (diagram + code prototype)

Goal:
Think beyond laptop-scale ML.

MONTH 12 — Year 2 Capstone

Final Major Project:

Build something substantial:

• Multi-model comparison system
• Automated training pipeline
• ML-powered decision support system

Requirements:

• Clean architecture
• Database
• API
• Documentation
• GitHub portfolio polished

Upload polished projects to GitHub
Share structured summary posts weekly on LinkedIn

End of Year 2 Outcome

If executed properly:

You will have:

• Advanced algorithm knowledge
• Strong probability & linear algebra
• Production-level ML pipeline understanding
• Internship-ready capability
• 15–20 serious projects
• Solid technical portfolio

At this stage, you could:

• Apply for international internships
• Contribute to serious open-source
• Freelance at higher level
• Enter competitive tech roles