arrow_back अभ्यास
Phase 5 • Week 21

Binary Trees finish, LLD begins (Intro + SOLID + UML), 3Blue1Brown's GPT chapters + Karpathy's makemore series

verified_user

Weekly Production Deliverable

Target Output
Deliverable: Binary Trees (Theory, Medium, FAQs, Construction, Morris) fully done. SOLID + UML done. You've walked the language-model lineage bigram → MLP → WaveNet with Karpathy.
Weeks: W21 Active W22 W23 W24 W25

Monday

0 / 2 done
DSA Zig Zag or Spiral Traversal; Boundary Traversal
1.5h
AI/ML Transformers Visual Intuition
3Blue1Brown — Neural Networks, Ch.5 "But what is a GPT? Visual intro to Transformers" & Ch.6 "Attention in transformers, visually explained" (Word vectors, high-dimensional spaces, context embeddings, self-attention mechanisms)
2.5h

Tuesday

0 / 2 done
DSA Vertical Order Traversal; Top View of BT; Bottom View of BT
1.5h
CORE LLD Intro, Design Principles & SOLID
Intro to Low-Level Design; Software Design Principles: DRY, KISS, YAGNI; SOLID Principles: Single Responsibility (SRP), Open/Closed (OCP), Liskov Substitution (LSP), Interface Segregation (ISP), Dependency Inversion (DIP) + Java code implementations + Quiz
2.5h

Wednesday

0 / 2 done
DSA Right View of BT; Left View of BT; Print root to leaf path in BT
1.5h
AI/ML Karpathy: makemore Part 1 & 2
Andrej Karpathy — "Neural Networks: Zero to Hero" ([YouTube]open_in_new): "Building makemore Part 1 (Bigram language model, counting vs neural net)" & "Part 2 (Multilayer Perceptron character-level LM based on Bengio et al. 2003)"
2.5h

Thursday

0 / 2 done
DSA LCA in BT; Maximum Width of BT LC #A
1.5h
CORE Unified Modeling Language (UML)
Class Diagrams, Object Diagrams, Relationships (Association, Aggregation, Composition, Generalization/Inheritance), Multiplicity + draw a complete UML class diagram for a real system (e.g. Library Management)
2.5h

Friday

0 / 2 done
DSA Print all nodes at a distance of K in BT; Minimum time to burn the BT from a given Node
1.5h
AI/ML Karpathy: makemore Part 3 & 4
Karpathy Zero to Hero: "Building makemore Part 3 (Activations, Gradients, Batch Normalization)" & "Part 4 (Becoming a Backprop Ninja — manual backprop through CrossEntropy, BatchNorm, Linear layers)"
2.5h
Weekend High-Load Execution • 8.0h Daily Deep Focus Lab

Saturday

0 / 3 done
DSA Count total nodes in a complete BT; Construct a BT from Preorder and Inorder; Construct a BT from Postorder and Inorder
1.5h
AI/ML Karpathy makemore Part 1 & 2 (4.0h)
Bigram model → MLP character-level language model (Bengio 2003); visualize negative log likelihood and embedding matrix.
4.0h
APT Quant M21 & Verbal/Logical
Quant M21 Permutation and Combination (Basic & Advance) + Verbal/Logical Mixed Practice
2.5h

Sunday

0 / 3 done
DSA Serialize and De-serialize BT; Morris Inorder Traversal; Morris Preorder Traversal + Contest + full Binary Trees revision
1.5h
AI/ML Karpathy makemore Part 3 & 4 (Backprop Ninja & WaveNet) (4.0h)
Implement BatchNorm manual backpropagation; build hierarchical WaveNet architecture; analyze gradient health.
4.0h
APT LLD Practice & makemore WaveNet
Karpathy makemore Part 5 (WaveNet architecture, hierarchical convolutions) + Practice: implement a clean, SOLID-compliant system in Java
2.5h
edit_note

Week 21 Technical Notes & Journal

#LeetCode #Java #DSA #Week21