AI PROGRAMME

Course Duration : 3 Months

ATHMOJYOTI CONSULTANCY SERVICES

Month 1: Introduction to AI & Basic Concepts

Module 1: Introduction to Artificial Intelligence

• What is AI?

  • Definition: AI refers to creating machines or software that can perform tasks that typically require human intelligence (e.g., visual perception, speech recognition, decision-making).

  • Types of AI:

    • Weak AI (Narrow AI): Designed to perform a specific task (e.g., voice assistants, image recognition).

    • Strong AI (General AI): Has the potential to perform any intellectual task that a human can do (still theoretical).

Example: Siri or Google Assistant is an example of Weak AI.

Module 2: Python for AI

• Installing Python and Libraries:

  • Install Python and set up essential libraries: NumPy, Pandas, Matplotlib, Scikit-learn, TensorFlow, Keras.

Example:

bash

CopyEdit

pip install numpy pandas matplotlib scikit-learn tensorflow keras

• Data Structures in Python:

  • Lists, tuples, dictionaries, sets for data storage and manipulation.

Example:

python

CopyEdit

my_list = [1, 2, 3, 4]

my_dict = {"name": "Alice", "age": 25}

• Basic Algorithms: Introduction to basic algorithms and how they work with Python.

Example:

python

CopyEdit

def factorial(n):

if n == 0:

     return 1

else:

     return n * factorial(n-1)

print(factorial(5))  # Output: 120

Month 2: Core AI Techniques

Module 3: Machine Learning Basics

• Introduction to Machine Learning:

  • Definition: Machine Learning (ML) is a subset of AI that focuses on building algorithms that learn from data and make predictions.

  • Types of ML:

    • Supervised Learning: Model is trained with labeled data (e.g., regression, classification).

    • Unsupervised Learning: Model is trained with unlabeled data (e.g., clustering).

    • Reinforcement Learning: Learning through trial and error (e.g., self-driving cars).

Example: Predicting house prices using supervised learning.

Supervised Learning:

• • Regression: Predicting continuous values.

  • Classification: Categorizing data into predefined classes.

Example (Linear Regression):

python

CopyEdit

from sklearn.linear_model import LinearRegression

import numpy as np

# Sample Data: House size vs Price

X = np.array([[1000], [1500], [2000], [2500], [3000]])  # Square footage

y = np.array([200000, 250000, 300000, 350000, 400000])  # Price in dollars

model = LinearRegression()

model.fit(X, y)

predicted_price = model.predict([[1200]])  # Predict price for 1200 sqft

print(predicted_price)  # Output: 220000

Module 4: Data Preprocessing and Feature Engineering

• Data Preprocessing:

  • Cleaning data (handling missing values, outliers).

  • Normalizing data (scaling values between 0 and 1).

Example:

python

CopyEdit

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()

scaled_data = scaler.fit_transform(data)  # Scaling the data

• Feature Engineering:

  • Feature Selection: Choosing relevant features for the model.

  • Feature Extraction: Transforming raw data into usable features.

Module 5: Supervised Learning Algorithms

• Linear Regression:

  • Predicts continuous values based on input features.

Example:

python

CopyEdit

from sklearn.linear_model import LinearRegression

model = LinearRegression()

model.fit(X_train, y_train)  # Train the model

predictions = model.predict(X_test)  # Make predictions

• Logistic Regression:

  • Used for binary classification problems (e.g., predicting whether an email is spam or not).

Example:

python

CopyEdit

from sklearn.linear_model import LogisticRegression

model = LogisticRegression()

model.fit(X_train, y_train)

predictions = model.predict(X_test)

• Decision Trees: Classifies data based on feature values by constructing a tree-like model.

Example:

python

CopyEdit

from sklearn.tree import DecisionTreeClassifier

model = DecisionTreeClassifier()

model.fit(X_train, y_train)

Month 3: Advanced AI Techniques & Projects

Module 6: Unsupervised Learning and Clustering

• K-Means Clustering:

  • A method for partitioning data into clusters based on similarity.

Example:

python

CopyEdit

from sklearn.cluster import KMeans

# Data points for clustering

data = [[1, 2], [1, 4], [1, 0], [4, 2], [4, 4], [4, 0]]

model = KMeans(n_clusters=2)

model.fit(data)

clusters = model.predict([[0, 0], [4, 4]])

print(clusters)  # Output: [1, 0] (cluster assignments)

Module 7: Deep Learning Fundamentals

• What is Deep Learning?:

  • A subset of machine learning using neural networks with multiple layers (also called deep neural networks).

• Introduction to Neural Networks:

  • Perceptrons: A basic neural network model for binary classification.

Example: Simple neural network using Keras.

python

CopyEdit

from keras.models import Sequential

from keras.layers import Dense

model = Sequential()

model.add(Dense(units=10, activation='relu', input_dim=5))  # Hidden Layer

model.add(Dense(units=1, activation='sigmoid'))  # Output Layer

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(X_train, y_train, epochs=10, batch_size=32)

Module 8: Natural Language Processing (NLP)

• Introduction to NLP:

  • Text Processing: Tokenization, stemming, lemmatization, and stopword removal.

Example (Tokenization):

python

CopyEdit

from nltk.tokenize import word_tokenize

text = "AI is transforming the world!"

tokens = word_tokenize(text)

print(tokens)  # Output: ['AI', 'is', 'transforming', 'the', 'world', '!']

• Text Classification: Use machine learning to classify text into categories.

Example (Sentiment Analysis):

python

CopyEdit

from sklearn.feature_extraction.text import CountVectorizer

from sklearn.naive_bayes import MultinomialNB

# Sample data

X = ["I love programming", "I hate bugs", "Python is great", "I dislike errors"]

y = [1, 0, 1, 0]  # 1 = positive, 0 = negative

vectorizer = CountVectorizer()

X_transformed = vectorizer.fit_transform(X)

model = MultinomialNB()

model.fit(X_transformed, y)

sentiment = model.predict(vectorizer.transform(["I love coding"]))

print(sentiment)  # Output: [1] (positive sentiment)

Module 9: Final Project - Build Your AI Application

• Project 1: Predictive Model for Housing Prices (Supervised Learning).

• Project 2: Sentiment Analysis using NLP.

• Project 3: Build a simple AI Chatbot using NLP and deep learning (optional).