Syllabus AIML BCA
Syllabus AIML BCA
I II III IV V VI Total
22 24 18 23 17 16 120
*SP-Specialization
*ID- Interdisciplinary
*F-Foundation
*GE- General Elective
AI-DS Specializations Subjects (BCA)
L T P
Semester Code Course Name Credits Type
(Hr.) (Hr.) (Hr.)
Introduction to Artificial
I BCA520A/B Intelligence Machine 3 0 2 4 SP
Learning and Data Science
Mathematical Foundation
for Artificial Intelligence
II BCA522A 4 0 0 4 SP
Machine Learning and Data
Science
ELECTIVE (Artificial
V Intelligence Machine 3 0 0 3 SP
Learning and Data Science)
Total 22 0 6 24
Semester – I
L T P Credi Contact
S. No. Code Course Name Type
(Hr.) (Hr.) (Hr.) ts Hours
Fundamental of Computers
1 BCA302A 4 0 0 4 4 CORE
& Programming in C
Introduction to Artificial
Intelligence Machine
2 BCA520A 3 0 0 3 3 SP
Learning and Data
Science
Fundamental of Computers
4 BCA303A 0 0 2 1 2 CORE
& Programming in C Lab
Introduction to Artificial
Intelligence Machine
5 BCA520B 0 0 2 1 1 SP
Learning and Data
Science Lab
Total 18 0 8 22 24
Semester – II
S. No. L T P Contact
Course Code Course Name Credits Type
(Hr.) (Hr.) (Hr.) Hours
Object Oriented
1 BCA126B 4 0 0 4 4 CORE
Programming Using C++
Operating
BCA113B/
2 System/Environmental 4 0 0 4 4 CORE
DCH001A
Studies
Database Management
3 BCA114B 4 0 0 4 4 CORE
Systems
Mathematical Foundation
for Artificial Intelligence
4 BCA522A 4 0 0 4 4 SP
Machine Learning and
Data Science
Database Management
6 BCA118B 0 0 2 1 2 CORE
Systems Lab
Professional
DEN002A/
8 Skills/Professional Skills 2 0 2 3 5 ID
DEN002B
Lab
Entrepreneurship
9 0 0 2 1 2 ID
Development
Total 19 0 10 24 29
Semester – III
S.N Course L T P Cred Course
Course Name Type
o. Code (Hr.) (Hr.) (Hr.) its Hours
Data Structures and
1 BCA305A 4 0 0 4 4 CORE
Algorithms
Programming in
3 BCA133B 4 0 0 4 4 CORE
JAVA
BCA176A/ Software
3 0 2 4 5 CORE
BCA121B Testing/Lab
Life Skills - 1
DEN003A (Personality 1 0 2 2 4 F
Development)
Total 17 0 08 18 25
Semester – IV
S. Contact
L T P Credit
No. Course Code Course Name Hours Type
(Hr.) (Hr.) (Hr.) s
Open Elective 3 0 0 3 3 GE
Total 17 0 4 23 27
Semester – V
S. No. L T P Cred Contac
Course Code Course Name Type
(Hr.) (Hr.) (Hr.) its t Hours
1 Information Security
BCA317A 4 0 0 4 4 CORE
Essentials
2 Departmental Elective-
3 0 2 4 4 CORE
III
5 Open Elective 3 0 0 3 3 GE
Total 14 0 6 17 19
Semester – VI
L P Cred
Course Code Course Name Type
(Hr.) (Hr.) its
Reference Books:
1) "Linear Algebra and Its Applications" by David C. Lay, Steven R. Lay, and Judi J. McDonald
2) "Probability and Statistics for Engineering and the Sciences" by Jay L. Devore
3) "Calculus: Early Transcendentals" by James Stewart
SEMESTER IV
BCA523A
Data Visualization Tools and Techniques
Unit I Introduction to Data Visualization
Definition and importance of data visualization, Principles of effective data visualization, Types of
data visualization: charts, graphs, maps, etc., Data visualization process: data acquisition,
exploration, analysis, visualization, interpretation, Ethical considerations and best practices in data
visualization
Unit II Basic Data Visualization Techniques
Introduction to basic visualization tools: Excel, Google Sheets, Tableau Public, etc., Creating and
customizing simple charts: bar charts, line charts, pie charts, scatter plots, etc., Adding labels, titles,
legends, and annotations to visualizations, Data filtering and sorting techniques for effective
visualization, Exporting and sharing visualizations
Unit III Advanced Data Visualization Techniques
Introduction to advanced visualization libraries: Matplotlib, Seaborn, Plotly, etc., Creating complex
and interactive visualizations using Python, Heatmaps, box plots, violin plots, histograms, etc.,
Geographic visualization: maps, choropleth maps, geospatial data visualization, Dashboard creation
and customization
Unit IV Data Visualization Best Practices
Choosing the right visualization for different types of data and analysis goals, Design principles for
effective visualization: color theory, layout, typography, etc., Data storytelling: conveying insights
and narratives through visualizations, Accessibility and inclusivity considerations in data
visualization, Critique and evaluation of data visualizations
Unit V Data Visualization Projects and Applications
Hands-on projects to apply data visualization techniques to real-world datasets, Exploratory data
analysis (EDA) through visualization, Case studies and examples of data visualization in various
domains: business, healthcare, finance, etc., Future trends and emerging technologies in data
visualization, Career opportunities and pathways in data visualization and related fields
Reference Books:
1) "Data Visualization: A Practical Introduction" by Kieran Healy
2) "Python Data Visualization: An Introduction to Data Visualization in Python with Matplotlib, Seaborn,
and Plotly" by Adel Osmani
3) "The Visual Display of Quantitative Information" by Edward Tufte
SEMESTER IV
BCA524A
Deep Learning
Unit I Introduction to Deep Learning
Definition and importance of Deep Learning, Historical overview and milestones in Deep Learning,
Comparison with traditional machine learning approaches, Basic concepts: neural networks,
activation functions, layers, etc., Applications of Deep Learning in various domains
Unit II Fundamentals of Neural Networks
Perceptrons and the McCulloch-Pitts model, Feedforward neural networks: architecture, forward
propagation, backpropagation, Activation functions: sigmoid, tanh, ReLU, etc., Loss functions and
optimization techniques: gradient descent, stochastic gradient descent, etc., Regularization
techniques: dropout, L2 regularization, etc.
Unit III Convolutional Neural Networks (CNNs)
Introduction to CNNs and their applications in computer vision, Convolutional layers: filters, feature
maps, receptive fields, Pooling layers: max pooling, average pooling, CNN architectures: LeNet,
AlexNet, VGG, ResNet, etc., Transfer learning and fine-tuning pre-trained CNNs
Unit IV Recurrent Neural Networks (RNNs)
Introduction to RNNs and their applications in sequential data analysis, Basic RNN architecture:
recurrent connections, hidden states, time-series data, Long Short-Term Memory (LSTM) networks
and Gated Recurrent Units (GRUs), Applications of RNNs: natural language processing, time series
prediction, etc., Challenges and limitations of RNNs
Unit V Advanced Topics in Deep Learning
Generative Adversarial Networks (GANs) and their applications in generative modeling,
Autoencoders and dimensionality reduction techniques, Attention mechanisms in Deep Learning,
Reinforcement Learning and its integration with Deep Learning, Future trends and emerging
technologies in Deep Learning
Reference Books:
1) "Deep Learning for Computer Vision" by Rajalingappaa Shanmugamani
2) "Neural Networks and Deep Learning: A Textbook" by Charu C. Aggarwal
3) "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
SEMESTER V
BCA526A
Python for Artificial Intelligence Machine Learning and Data Science
Unit I Advanced Python Programming
Functional programming in Python: lambda functions, map, filter, reduce, Object-oriented
programming (OOP) concepts: classes, inheritance, polymorphism, Decorators and context
managers, Generators and iterators, Exception handling and error reporting.
Unit II Data Handling and Manipulation with Python
Advanced data manipulation with Pandas: groupby, pivot tables, time series data, Working with large
datasets: memory optimization techniques, Advanced data cleaning techniques: handling missing
data, outlier detection and removal, Merging and joining datasets, Introduction to data serialization
formats: JSON, XML, YAML
Unit III Advanced Data Visualization with Python
Interactive visualization with Plotly and Bokeh, Customizing visualizations with Matplotlib and
Seaborn: advanced plotting techniques, themes, styles, 3D visualization with Matplotlib and Plotly,
Dashboards and interactive applications using Dash, Introduction to geospatial data visualization
with GeoPandas and Folium
Unit IV Advanced Machine Learning Techniques
Ensemble learning methods: Random Forest, Gradient Boosting, AdaBoost, Kernel methods: Support
Vector Machines (SVM), Kernel Ridge Regression, Unsupervised learning techniques: Clustering
(K-Means, DBSCAN), Dimensionality Reduction (PCA, t-SNE), Semi-supervised and self-
supervised learning, Anomaly detection algorithms
Unit V Deep Learning with Python
Advanced topics in deep learning: advanced architectures (Capsule Networks, Transformer
Networks), attention mechanisms, adversarial training, Advanced techniques for training deep neural
networks: transfer learning, curriculum learning, learning rate schedules, Model optimization
techniques: model compression, quantization, pruning, Introduction to distributed deep learning with
TensorFlow and PyTorch, Advanced applications of deep learning: natural language processing,
computer vision, reinforcement learning
Reference Books:
1) "Python for Data Analysis" by Wes McKinney
2) "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" by Aurélien Géron
3) "Pattern Recognition and Machine Learning" by Christopher M. Bishop
4) "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
Practical
Subject Introduction to Artificial Intelligence Machine Learning and Data Science Lab
Code BCA520B
Credit 1
Course Outcomes:
Students explore supervised and unsupervised learning techniques, and apply advanced concepts to real-
world scenarios. By mastering data analysis and visualization, students gain the skills needed to excel in
diverse industries.
Exercises—
1) Load a dataset (e.g., Iris dataset, Titanic dataset) into Python using Pandas. Explore the dataset by:
Displaying the first few rows.
Checking for missing values.
Calculating summary statistics.
Visualizing distributions of numerical variables.
2) Perform data preprocessing tasks such as:
Handling missing values (e.g., imputation, deletion).
Encoding categorical variables (e.g., one-hot encoding, label encoding).
Scaling numerical features (e.g., standardization, normalization).
3) Implement a supervised learning algorithm (e.g., decision tree classifier, logistic regression) using
Scikit-learn. Train the model on a training set and evaluate its performance on a test set using
appropriate metrics (e.g., accuracy, precision, recall, F1-score).
4) Experiment with different hyperparameters of the supervised learning model (e.g., max_depth for
decision trees, C for logistic regression) and observe how they affect model performance.
5) Apply an unsupervised learning algorithm (e.g., K-means clustering, hierarchical clustering) to a
dataset. Explore the resulting clusters and interpret the findings.
6) Use dimensionality reduction techniques (e.g., Principal Component Analysis, t-SNE) to visualize
high-dimensional data in two or three dimensions. Discuss the insights gained from the visualization.
7) Split a dataset into training and testing sets using cross-validation techniques (e.g., k-fold cross-
validation, stratified cross-validation). Train a machine learning model on multiple folds and
compute the average performance metrics.
8) Perform model selection by comparing the performance of multiple algorithms (e.g., decision tree,
random forest, support vector machine) on a given dataset. Choose the best-performing model based
on evaluation metrics.
9) Explore ensemble learning techniques (e.g., bagging, boosting) by implementing ensemble models
such as Random Forest or Gradient Boosting Machines. Compare the performance of ensemble
models with individual base models.
10) Implement a neural network model using TensorFlow or PyTorch. Design the architecture of the
neural network (e.g., number of layers, activation functions) and train the model on a dataset.
Evaluate the performance of the neural network on a test set.
11) Choose a real-world dataset related to a specific domain (e.g., healthcare, finance, retail). Apply
appropriate machine learning techniques to solve a relevant problem, such as predicting customer
churn, diagnosing diseases, or forecasting stock prices.
12) Present the results of your analysis in a clear and interpretable manner, using data visualization
techniques (e.g., plots, charts) to communicate insights to stakeholders.
Subject Python for Artificial Intelligence Machine Learning and Data Science Lab
Code BCA521B
Credit 1
Course Outcomes:
Students learn model evaluation, optimization, and ethical considerations, fostering critical thinking and
effective communication for real-world applications. By mastering these concepts, students are prepared to
tackle complex data challenges and contribute responsibly to the field of Artificial Intelligence and Data
Science.
Exercises—
1) Load a dataset using Pandas and perform basic data exploration tasks such as checking for missing
values and visualizing data distributions.
2) Preprocess the data by handling missing values, encoding categorical variables, and scaling
numerical features.
3) Load a dataset using Pandas and perform basic data exploration tasks such as checking for missing
values and visualizing data distributions.
4) Preprocess the data by handling missing values, encoding categorical variables, and scaling
numerical features.
5) Load a dataset using Pandas and perform basic data exploration tasks such as checking for missing
values and visualizing data distributions.
6) Preprocess the data by handling missing values, encoding categorical variables, and scaling
numerical features.
7) Load a dataset using Pandas and perform basic data exploration tasks such as checking for missing
values and visualizing data distributions.
8) Preprocess the data by handling missing values, encoding categorical variables, and scaling
numerical features.
9) Load a dataset using Pandas and perform basic data exploration tasks such as checking for missing
values and visualizing data distributions.
10) Preprocess the data by handling missing values, encoding categorical variables, and scaling
numerical features.
11) Load a dataset using Pandas and perform basic data exploration tasks such as checking for missing
values and visualizing data distributions.
12) Preprocess the data by handling missing values, encoding categorical variables, and scaling
numerical features.
13) Load a dataset using Pandas and perform basic data exploration tasks such as checking for missing
values and visualizing data distributions.
14) Preprocess the data by handling missing values, encoding categorical variables, and scaling
numerical features.
Code BCA523B
Credit 1
Course Outcomes: Students gain proficiency in basic and advanced techniques, enabling them to analyze
complex datasets effectively. Through critical analysis and practical projects, they develop skills in tool
comparison, visualization design, and ethical data handling. Ultimately, the course fosters adaptability and
continuous learning, preparing students to excel in the dynamic landscape of data visualization.
Exercises—
1. Install Tableau Desktop or any other data visualization tool of your choice.
2. Import a sample dataset (e.g., CSV file containing sales data).
3. Create a simple bar chart showing monthly sales revenue.
4. Customize the chart by adding labels, colors, and a title.
5. Save the visualization as an image or PDF file.
6. Install Matplotlib and Seaborn Python libraries.
7. Load a dataset (e.g., Iris dataset) using Pandas.
8. Create scatter plots to visualize relationships between different variables.
9. Use Matplotlib to create a line plot showing the trend of a numerical variable over time.
10. Explore different plot styles and color palettes offered by Seaborn.
11. Install Tableau Desktop or any other data visualization tool of your choice.
12. Import a sample dataset (e.g., CSV file containing sales data).
13. Create a simple bar chart showing monthly sales revenue.
14. Customize the chart by adding labels, colors, and a title.
15. Save the visualization as an image or PDF file.
16. Install Tableau Desktop or any other data visualization tool of your choice.
17. Import a sample dataset (e.g., CSV file containing sales data).
18. Create a simple bar chart showing monthly sales revenue.
19. Customize the chart by adding labels, colors, and a title.
20. Save the visualization as an image or PDF file.