LLMs (Ch11) and Generative Image Models (Ch12) initial code. Improved README files.

Update README.md

Mostly working code.

Clean up.

Refactors.

Comment fixes for LLMs.

Print fixes for LLMs.

Improved variable names in LLM.

Clean up.

Comment tweaks.

Comment tweaks.

README improvements.

LLMs (Ch11), and Generative Image Models (Ch12) initial code. README improvements.

LLMs (Ch11) and Generative Image Models (Ch12) initial code. Improved README files.

Author: rishal-hurbans

README.md

@@ -2,12 +2,19 @@
 
 [Get Grokking Artificial Intelligence Algorithms at Manning Publications](https://www.manning.com/books/grokking-artificial-intelligence-algorithms?a_aid=gaia&a_bid=6a1b836a) 
 
+Rather Learn by exploring the code notebook in your browser? Click here:
+
+[![Open the interactive code notebook](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/rishal-hurbans/Grokking-Artificial-Intelligence-Algorithms-Notebook/blob/main/Grokking_Artificial_Intelligence_Algorithms_Notebook.ipynb)
+
 ## Requirements
 * Python 3.7.0+
 * Pip 3
 
 ## Setup
 Make sure that you have Python 3.7.0+ installed. [Download Python here](https://www.python.org/downloads/).
+pip3 should be installed with Python 3.7.0+ on macOS and Windows. You may need to install pip3 seperately if you're using Linux.
+Use the ```sudo apt-get install python3-pip``` command if you're using Ubuntu or Debian Linux.
+Use the ```sudo yum install python3-pip``` command if you're using Fedora Linux. 
 
 Clone this repository.
 

ch01-intuition_of_ai/README.md

@@ -4,4 +4,4 @@ Intelligence is a mystery. Intelligence is a concept that has no agreed upon def
 This directory does not contain any code since there are no specific algorithm implementations discussed in Chapter 1.
 
 ## Summary
-![Chapter 1 summary](readme_assets/Ch1-Summary.png)
+![Chapter 1 summary](readme_assets/Ch1-Summary.png)

ch02-search_fundamentals/README.md

@@ -7,4 +7,21 @@ Think about when you explore things you want to learn. Some might look at a wide
 ![BFS and DFS](readme_assets/Bfs-Dfs-Combined.png)
 
 ## Summary
-![Chapter 2 summary](readme_assets/Ch2-Summary.png)
+![Chapter 2 summary](readme_assets/Ch2-Summary.png)
+
+## What's Included
+- Breadth-first Search (BFS) and Depth-first Search (DFS) on a simple maze.
+- Problem representation and state expansion basics.
+
+## Key Scripts
+- `uninformed_search/maze_bfs.py`: BFS over a grid maze.
+- `uninformed_search/maze_dfs.py`: DFS over a grid maze.
+- `uninformed_search/maze_puzzle.py`: Maze definition and utilities.
+
+## How To Run
+- From this folder:
+  - `python3 uninformed_search/maze_bfs.py`
+  - `python3 uninformed_search/maze_dfs.py`
+
+## Notes
+- Compare traversal order and path length differences between BFS and DFS.

ch03-intelligent_search/README.md

@@ -17,3 +17,23 @@ Min-max search aims to build a tree of possible outcomes based on moves that eac
 
 ## Summary
 ![Chapter 3 summary](readme_assets/Ch3-Summary.png) 
+
+## What's Included
+- A* search with heuristic guidance on a maze.
+- Adversarial search with min‑max and alpha‑beta pruning.
+
+## Key Scripts
+- `informed_search/maze_astar.py`: A* pathfinding example.
+- `adversarial_search/connect_puzzle.py`: Game state mechanics.
+- `adversarial_search/connect_ai.py`: Min‑max AI for Connect.
+- `adversarial_search/connect_ai_alpha_beta_pruning.py`: Alpha‑beta optimized AI.
+- `adversarial_search/connect_puzzle_game.py`: Simple playable loop.
+
+## How To Run
+- A*:
+  - `python3 informed_search/maze_astar.py`
+- Connect AI demo:
+  - `python3 adversarial_search/connect_puzzle_game.py`
+
+## Notes
+- Try varying search depth in the adversarial AI to observe strength vs. speed trade‑offs.

ch03-intelligent_search/adversarial_search/connect_ai_alpha_beta_pruning.py

@@ -38,7 +38,8 @@ def minmax(connect, depth, min_or_max, move, alpha, beta):
     best_score = INFINITY_NEGATIVE * min_or_max
     best_max_move = -1
     # Get possible moves given the board size
-    moves = random.sample(range(0, connect.board_size_y + 1), connect.board_size_x)
+    # Sample all possible column slots along the X dimension
+    moves = random.sample(range(0, connect.board_size_x), connect.board_size_x)
     for slot in moves:
         neighbor = copy.deepcopy(connect)
         move_outcome = neighbor.play_move(slot)

ch03-intelligent_search/adversarial_search/connect_puzzle.py

@@ -133,7 +133,7 @@ def execute_move(self, player, slot_number):
 
     # Execute a move for a player if there's space in the slot and choose the player based on whose turn it is
     def play_move(self, slot):
-        if 0 <= slot <= 4:
+        if 0 <= slot < self.board_size_x:
             if not self.is_slot_full(slot):
                 if self.player_turn == PLAYERS[PLAYER_AI]:
                     self.execute_move(PLAYER_AI, slot)

ch04-evolutionary_algorithms/README.md

@@ -7,4 +7,20 @@ The example used is the Knapsack Problem. The Knapsack Problem has number of ite
 ![Knapsack encoding](readme_assets/Knapsack_Encoding.png)
 
 ## Summary
-![Chapter 4 summary](readme_assets/Ch4-Summary.png)
+![Chapter 4 summary](readme_assets/Ch4-Summary.png)
+
+## What's Included
+- Brute‑force and Genetic Algorithm (GA) solutions to the Knapsack problem.
+- Binary encoding of solutions, fitness evaluation, crossover, and mutation.
+
+## Key Scripts
+- `knapsack_brute_force.py`: Exhaustive enumeration of feasible packs.
+- `knapsack_genetic_algorithm.py`: GA search with configurable hyperparameters.
+
+## How To Run
+- From this folder:
+  - `python3 knapsack_brute_force.py`
+  - `python3 knapsack_genetic_algorithm.py`
+
+## Notes
+- Adjust population size, mutation rate, and generations to see convergence behavior.

ch05-advanced_evolutionary_approaches/README.md

@@ -2,4 +2,17 @@
 Nothing to see here. Refer to the code in ch04-evolutionary-algorithms.
 
 ## Summary
-![Chapter 5 summary](readme_assets/Ch5-Summary.png)
+![Chapter 5 summary](readme_assets/Ch5-Summary.png)
+
+## What's Included
+- Conceptual pointers beyond the basic GA (selection strategies, elitism, hybridization).
+- Code examples continue in Chapter 4’s folder.
+
+## Key Scripts
+- Refer to Chapter 4 (`ch04-evolutionary_algorithms`).
+
+## How To Run
+- See Chapter 4 run instructions.
+
+## Notes
+- Use this chapter as a springboard to experiment with GA variants in `ch04`.

ch06-swarm_intelligence-ants/README.md

@@ -7,3 +7,20 @@ The Ant Colony Optimization algorithm is inspired by the behavior of ants moving
 
 ## Summary
 ![Chapter 6 summary](readme_assets/Ch6-Summary.png)
+
+## What's Included
+- Ant Colony Optimization (ACO) on a set of attractions with distances.
+- Pheromone trails, evaporation, and probabilistic path construction.
+
+## Key Scripts
+- `carnival_brute_force.py`: Exhaustive tour construction for small instances.
+- `carnival_aco.py`: ACO solver with pheromone updates and evaporation.
+- CSV data: `attractions-*.csv` distance matrices.
+
+## How To Run
+- From this folder:
+  - `python3 carnival_brute_force.py`
+  - `python3 carnival_aco.py`
+
+## Notes
+- Tweak parameters (alpha, beta, evaporation rate, ant count) to see convergence on different datasets.

ch06-swarm_intelligence-ants/__init__.py

@@ -0,0 +1,2 @@
+"""Chapter 6: Swarm Intelligence (Ants) package init."""
+