BCA507

Course Title : AI-driven Data Science
Course Code : BCA507

Course Learning Outcomes:
On the completion of the course, students will be able to:
 Develop critical thinking and problem-solving skills by applying AI and machine learning techniques.
 Gain technical proficiency in using industry-standard tools and frameworks for AI and data science.
 Improve collaboration and communication skills by working on case studies and presenting findings effectively.
Detailed Syllabus:
Unit – 1 Introduction to Artificial Intelligence:
What Is AI?,The Foundations of Artificial Intelligence, The History of Artificial Intelligence, Applications of AI, Risks
and Benefits of AI, Types of AI: Narrow AI, General AI, and Superintelligent AI, Intelligent agents and environments,
Problem-solving in AI, Search algorithms (uninformed and informed search).
Unit – 2 Machine Learning Basics:

What Is Machine Learning?, Why Use Machine Learning?, Types of Machine Learning Systems,Batch and Online
Learning,Instance-Based Versus Model-Based Learning, Challenges of Machine Learning, Testing and Validating
dataset(Hyperparameter Tuning and Model Selection, Data Mismatch), Working with classification (MNIST),
Training a Binary Classifier,Performance Measures (Measuring Accuracy Using Cross-Validation,Confusion
Matrix,Precision and Recall, The ROC Curve.
Unit – 3 Custom Models and Training with TensorFlow:

A Quick Tour of TensorFlow, Using TensorFlow like NumPy :Tensors and Operations, Type Conversions,
Variables,Other Data Structures, Customizing Models and Training Algorithms: Saving and Loading Models,
Custom Activation Functions, Initializers, Regularizers, and Constraints,Custom Metrics, Custom Layers, Custom
Models, TensorFlow Functions and Graphs: Autograph and Tracing, TF Function Rules, The Data API:
Chaining Transformations, Shuffling the Data, Preprocessing the Data, Using the Dataset With tf.keras, The
TensorFlow Datasets (TFDS).
Unit - 4 Neural Networks and Deep Learning:

Learning representations from data, The “deep” in deep learning, Understanding how deep learning works,
Decision trees, random forests, and gradient boosting machines, Why deep learning? Why now?, Introduction of
a neural network, Layers: the building blocks of deep learning, Models: networks of layers,Loss functions and
optimizers:
keys to configuring the learning process.
Unit – 5 Case Study: AI and Data Science in Practice

Introduction : Objective, Problem Statement, Data Collection : Data Sources, Data Types, Data Quality, Data
Preparation : Data Cleaning, Data Transformation, Exploratory Data Analysis (EDA), Feature Engineering, Model
Selection and Training : Algorithm Choice, Model Training, Hyperparameter Tuning, Model Evaluation
:Evaluation Metrics, Validation Techniques, Comparison, Implementation :Deployment, Integration, Monitoring,
Results and Discussion : Findings, Impact, Limitations, Conclusion : Summary, Future Work, Appendices and
References : Documentation, References , Presentation : Visualization , Report
Examples :
Geosciences : Predicting Landslides in the Western Ghats of India using Data Science.
Healthcare : Improving Diabetes Diagnosis and Management in Rural India.
Logistics : An e-commerce company in India faced high transportation costs and frequent delivery delays. They
sought to optimize their logistics operations using data science.
Banking: Fraud Detection for a Leading Bank in India.
E- Commerce : An e-commerce company in India faced challenges in inventory management, customer
personalization, and demand forecasting. They aimed to optimize these operations using data science.
Agriculture : A farming cooperative in India faced challenges in predicting crop yields, optimizing resource usage,
and managing pest infestations. They sought to leverage data science to improve their agricultural practices.
Text Books:
1. Artificial intelligence: a modern approach" by stuart russell and peter norvig
2. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" by Aurélien Géron
3. Deep Learning with Python by François Chollet
Course Outcomes :
1. Understand the basic concepts, history, and various applications of artificial intelligence.
2. Implement and compare different search algorithms (uninformed and informed search).
3. Grasp the fundamental concepts of machine learning, including different types of learning systems and the
challenges involved.
4. Train and test machine learning models, including binary classifiers, and assess model performance using metrics
like cross-validation, confusion matrix, precision, recall, and ROC curve.
5. Gain proficiency in using TensorFlow for creating and managing models, including custom activation functions,
initializers, regularizers, and constraints.
6. Customize models and training algorithms to address specific data science problems, and effectively save, load,
and deploy TensorFlow models in practical applications.
7. Learn the principles of deep learning, including learning representations from data, and explore various deep
learning architectures like decision trees, random forests, and gradient boosting machines.
8. Build and configure neural networks using layers and models.
9. Conduct comprehensive case studies and apply the complete data science process, from problem statement to
implementation, in real-world scenarios.
10. Communicate the results and impact of data science projects effectively, identify limitations, and suggest future
work based on case study outcomes.
Chapters as per Units

Unit - 1 : Book - 1 (CH- 1.1, 1.3,1.4,1.5, 2.1, 3.1, 3.3)
Unit - 2 : Book - 2 (CH-1,2,3 )
Unit - 3 : Book - 2 (CH-12, 13)
Unit - 4 : Book - 3 (CH-1 , 1.1.3,1.1.4, 1.1.5, 1.2.4, 1.3, 3.1)

BCA507

Uploaded by

Copyright:

Available Formats

BCA507

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

BCA507

Uploaded by

Copyright:

Available Formats

Course Title : AI-driven Data Science

Course Code : BCA507

Unit – 2 Machine Learning Basics:

Unit – 3 Custom Models and Training with TensorFlow:

Unit - 4 Neural Networks and Deep Learning:

Unit – 5 Case Study: AI and Data Science in Practice

Chapters as per Units

You might also like