AI_foundations

Types of Machine Learning Machine learning (ML) is a subset of artificial intelligence that enables systems to learn patterns from data and make predictions. It is generally categorized into the following types: Supervised Learning The model is trained on labeled data (i.e., data with known outputs). The goal is to learn the mapping from inputs to correct outputs. Common applications: Spam detection, Image classification, Stock price prediction Example: from sklearn.linear_model import LinearRegression import numpy as np x_train = np.array([1, 2, 3, 4, 5]).reshape(-1, 1) y_train = np.array([30, 35, 40, 50, 60]) model = LinearRegression() model.fit(x_train, y_train) print("Predicted salary for 6 years of experience:", model.predict([[6]])[0]) Unsupervised Learning The model is trained on unlabeled data (i.e., no predefined outputs). The goal is to find hidden structures or patterns in data. Common applications: Customer segmentation, Anomaly detection, Market basket analysis Example: from sklearn.cluster import KMeans import numpy as np data = np.array([[2, 3], [10, 15], [5, 8], [12, 14], [6, 9]]) kmeans = KMeans(n_clusters=2, random_state=42) kmeans.fit(data) print("Cluster assignments:", kmeans.labels_) Reinforcement Learning (RL) The model learns through trial and error and receives rewards or penalties based on actions. Used in game AI, robotics, and autonomous systems. Includes Proximal Policy Optimization (PPO), Generalized Proximal Policy Optimization (GRPO). Example: Self-learning game AI like AlphaGo. Value-Based vs. Rule-Based Learning Value-Based Learning: The AI assigns numerical values to different outcomes and chooses actions maximizing future rewards (e.g., Q-learning in RL). Rule-Based Learning: The AI follows predefined rules (e.g., Decision Trees, Expert Systems). Regression & Classification Basics Machine learning models are not only categorized into regression and classification but also include reinforcement learning and generative models. However, regression and classification are the most fundamental predictive learning approaches. ...

What is AI? Artificial Intelligence (AI) refers to the ability of machines or software to perform tasks that typically require human intelligence. These tasks include learning, reasoning, problem-solving, understanding language, and recognizing patterns. Defining Intelligence To fully understand AI, we must first define intelligence itself. Intelligence encompasses: Reasoning: The ability to process information logically and draw conclusions. Learning: Acquiring knowledge from data and experience. Innovation: The ability to create new solutions rather than just repeating known ones. Adaptation: Adjusting responses based on changing environments. Emotion and Creativity: While humans experience emotions and creative thinking, there is an ongoing debate on whether AI can or should replicate these aspects. AI is often seen as intelligent because it mimics these traits, particularly in pattern recognition, learning from data, and generating human-like responses. Large Language Models (LLMs), like ChatGPT, create the illusion of intelligence by predicting the most likely words or sequences based on vast datasets. While they do not understand concepts like humans do, they generate responses that appear intelligent through probabilistic modeling. ...

History of Python Python was created by Guido van Rossum and first released in 1991. It was designed to be a simple, readable, and easy-to-use language, drawing inspiration from languages like ABC, C, and Perl. Over the years, Python has grown into one of the most widely used programming languages in the world, particularly in AI and data science. Relation Between Python and Other Programming Languages Python is often compared with other programming languages based on its usability, performance, and ecosystem: ...

AI Bias & Fairness AI systems are trained on large datasets, which can introduce biases if the data is not representative of diverse populations. AI bias can result in unfair treatment in various domains, such as hiring, lending, and law enforcement. 1. Types of AI Bias Data Bias: If training data is unbalanced (e.g., containing more data for one group than another), predictions may be unfair. Algorithmic Bias: Certain AI models may favor specific outcomes based on their structure. Human Bias: The developers’ assumptions and societal biases can influence AI decisions. 2. Example: AI Bias in Hiring AI-driven hiring tools have been found to favor certain demographics. ...

Creating AI-Based Games AI has revolutionized the gaming industry by providing intelligent NPCs (Non-Player Characters), procedural content generation, and adaptive gameplay. 1. AI for Game Bots & Pathfinding Game AI often includes pathfinding algorithms, which allow NPCs to navigate environments dynamically. One of the most commonly used algorithms is A* (A-star). import heapq def heuristic(a, b): return abs(a[0] - b[0]) + abs(a[1] - b[1]) def astar(grid, start, goal): open_list = [] heapq.heappush(open_list, (0, start)) came_from = {} g_score = {start: 0} f_score = {start: heuristic(start, goal)} while open_list: _, current = heapq.heappop(open_list) if current == goal: path = [] while current in came_from: path.append(current) current = came_from[current] return path[::-1] for neighbor in [(0,1), (1,0), (0,-1), (-1,0)]: next_node = (current[0] + neighbor[0], current[1] + neighbor[1]) if next_node not in grid: continue temp_g_score = g_score[current] + 1 if next_node not in g_score or temp_g_score < g_score[next_node]: g_score[next_node] = temp_g_score f_score[next_node] = temp_g_score + heuristic(next_node, goal) heapq.heappush(open_list, (f_score[next_node], next_node)) came_from[next_node] = current return [] This algorithm is widely used in games like Pac-Man, strategy games, and RPGs to allow NPCs to navigate the map. ...