Welcome!
SECOND HALF OF 2026
Department of Artificial Intelligence & Data Science
Dr. S. M. Patil
M.E., PhD (CSE) ,LLB
Prof. S. M. Patil, SIGCE, Department of AI & DS
VISION
To emerge as a center of excellence in the field of Artificial Intelligence and Data Science education, research , innovation, and societal,ethical solutions to national and global challenges.s.
Prof. S. M. Patil, SIGCE, Department of AI & DS
MISSION
M1: To deliver high-quality education in AI and Data Science that nurtures academic excellence, human values, and a spirit of innovation.
M2: To promote interdisciplinary research and collaborative initiatives that contribute to technological advancements and societal development.
M3: Empower students to become exceptional professionals with strong ethical values, equipped to create, develop, and lead global engineering enterprises.
Prof. S. M. Patil, SIGCE, Department of AI & DS
Knowledge and Attitude Profile (WK)
Prof. S. M. Patil, SIGCE, Department of AI & DS
WK1: A systematic, theory-based understanding of the natural sciences applicable to the discipline and awareness of relevant social sciences.
WK2: Conceptually-based mathematics, numerical analysis, data analysis, statistics and formal aspects of computer and information science to support detailed analysis and modelling applicable to the discipline.
WK3: A systematic, theory-based formulation of engineering fundamentals required in the engineering discipline.
WK4: Engineering specialist knowledge that provides theoretical frameworks and bodies of knowledge for the accepted practice areas in the engineering discipline; much is at the forefront of the discipline.
WK5: Knowledge, including efficient resource use, environmental impacts, whole-life cost,reuse of resources, net zero carbon, and similar concepts, that supports engineering design and operations in a practice area.
WK6: Knowledge of engineering practice (technology) in the practice areas in the engineering discipline.
WK7: Knowledge of the role of engineering in society and identified issues in engineering practice in the discipline, such as the professional responsibility of an engineer to public safety and sustainable development.
WK8: Engagement with selected knowledge in the current research literature of the discipline, awareness of the power of critical thinking and creative approaches to evaluate emerging issues.
WK9: Ethics, inclusive behavior and conduct. Knowledge of professional ethics, responsibilities, and norms of engineering practice. Awareness of the need for diversity by reason of ethnicity, gender, age, physical ability etc. with mutual understanding and respect, and of inclusive attitudes.
Program Outcomes (PO)
Prof. S. M. Patil, SIGCE, Depart
ent of AI & DS
PO1: Engineering Knowledge: Apply knowledge of mathematics, natural science, computing, engineering fundamentals and an engineering specialization as specified in WK1 to WK4 respectively to develop to the solution of complex engineering problems.
PO2: Problem Analysis: Identify, formulate, review research literature and analyze complex engineering problems reaching substantiated conclusions with consideration for sustainable development. (WK1 to WK4)
PO3: Design/Development of Solutions: Design creative solutions for complex engineering problems and design/develop systems/components/processes to meet identified needs with consideration for the public health and safety, whole-life cost, net zero carbon, culture, society and environment as required. (WK5)
PO4: Conduct Investigations of Complex Problems: Conduct investigations of complex engineering problems using research-based knowledge including design of experiments, modelling, analysis & interpretation of data to provide valid conclusions. (WK8).
PO5: Engineering Tool Usage: Create, select and apply appropriate techniques, resources and modern engineering & IT tools, including prediction and modelling recognizing their limitations to solve complex engineering problems. (WK2 and WK6)
PO6: The Engineer and The World: Analyze and evaluate societal and environmental aspects while solving complex engineering problems for its impact on sustainability with reference to economy, health, safety, legal framework, culture and environment. (WK1, WK5, and WK7).
Program Outcomes (PO)
Prof. S. M. Patil, SIGCE, Depart
ent of AI & DS
PO7: Ethics: Apply ethical principles and commit to professional ethics, human values, diversity and inclusion; adhere to national & international laws. (WK9)
PO8: Individual and Collaborative Team work: Function effectively as an individual, and as a member or leader in diverse/multi-disciplinary teams.
PO9: Communication: Communicate effectively and inclusively within the engineering community and society at large, such as being able to comprehend and write effective reports and design documentation, make effective presentations considering cultural, language, and learning differences
PO10: Project Management and Finance: Apply knowledge and understanding of engineering management principles and economic decision-making and apply these to one’s own work, as a member and leader in a team, and to manage projects and in multidisciplinary environments.
PO11: Life-Long Learning: Recognize the need for, and have the preparation and ability for i) independent and life-long learning ii) adaptability to new and emerging technologies and iii) critical thinking in the broadest context of technological change. (WK8)
Program Specific Outcomes (PSO)
PSO1: Apply the knowledge of Artificial Intelligence, Machine Learning, Deep Learning, and Data Science techniques to design intelligent systems and solve real-world problems.
PSO2: Use modern tools, programming languages, and frameworks to build intelligent systems and data-driven applications.
Prof. S. M. Patil, SIGCE, Department of AI & DS
PSO3: Develop AI solutions that are socially responsible, ethically sound, and aligned with sustainable development goals.
COURSE NAME
Deep Learning
SEM-VII
SUBJECT CODE: CSC701
Prof. S. M. Patil, SIGCE, Department of AI & DS
Deep Learning
Course Code | CSC701 | Marks | |
Course Name | Deep Learning | Internal Assessment | |
| | TEST 1 (20 M) | |
| | TEST 2 (20 M) | |
| | AVG | 20 |
| | End Semester Examination | 80 |
| | TOTAL MARKS | 100 |
Prof. S. M. Patil, SIGCE, Department of AI & DS
Deep Learning
Teaching Scheme (Hrs/week) | Credit Assigned | |||||
TH | OR | TUT | TH | OR | TUT | TOTAL |
3 | - | - | 3 | - | - | 3 |
Prof. S. M. Patil, SIGCE, Department of AI & DS
Course Objectives: Students will be able
1. To learn the fundamentals of Neural Network.
2. To gain an in-depth understanding of training Deep Neural Networks.
3. To acquire knowledge of advanced concepts of Convolution Neural Networks, Autoencoders and Recurrent Neural Networks.
4. Students should be familiar with the recent trends in Deep Learning.
Prof. S. M. Patil, SIGCE, Department of AI & DS
Course Outcomes:
CO1: Gain basic knowledge of Neural Networks.
�CO2: Acquire in depth understanding of training Deep Neural Networks.�
CO3: Design appropriate DNN model for supervised, unsupervised and sequence learning applications.
�CO4: Gain familiarity with recent trends and applications of Deep Learning.
Prof. S. M. Patil, SIGCE, Department of AI & DS
Deep Learning
CO | PO1 | PO2 | PO3 | PO4 | PO5 | PO6 | PO7 | PO8 | PO9 | PO10 | PO11 | PO12 | PSO1 | PSO2 |
CO1 | 3 | 2 | - | - | 2 | - | - | - | - | - | - | 1 | 3 | |
CO2 | 3 | 3 | 3 | - | 2 | - | - | - | - | - | - | 1 | 3 | 3 |
CO3 | 3 | 2 | 2 | 2 | 2 | - | - | - | - | - | - | 1 | 3 | 3 |
CO4 | 2 | 2 | 2 | 2 | 2 | - | - | - | - | - | - | 1 | 3 | 3 |
Prof. S. M. Patil, SIGCE, Department of AI & DS
Prof. S. M. Patil, SIGCE, Department of AI & DS
SYLLABUS
Sr. No. | Module | Detailed Content |
01 | Fundamentals of Neural Network | History of Deep Learning, Deep Learning Success Stories, Multilayer Perceptrons (MLPs), Representation Power of MLPs, Sigmoid Neurons, Gradient Descent, Feedforward Neural Networks. Deep Networks: Three Classes of Deep Learning, Basic Terminologies. |
02 | Training, Optimization & Regularization of DNN | Multi Layered Feed Forward NN, Activation functions (Tanh, Logistic, ReLU, Leaky ReLU), Loss functions. Optimization: Backpropagation, GD variants (SGD, Mini Batch, Momentum, Nesterov, AdaGrad, Adam, RMSProp). Regularization: L1/L2, Dropout, Batch Normalization, Data Augmentation. |
03 | Autoencoders: Unsupervised Learning | Linear, Undercomplete, Overcomplete Autoencoders. Denoising, Sparse, Contractive Autoencoders. Application: Image Compression. |
Prof. S. M. Patil, SIGCE, Department of AI & DS
SYLLABUS
Sr. No. | Module | Detailed Content |
04 | Convolutional Neural Networks (CNN) | Convolution operation, Padding, Stride, CNN architecture: Convolution & Pooling layers. Weight Sharing, Multichannel convolution. Modern Architectures: LeNet, AlexNet, ResNet. |
05 | Recurrent Neural Networks (RNN) | Sequence Learning, Unfolding Computational Graphs, Bidirectional RNN, BPTT, Vanishing & Exploding Gradients. LSTM: Selective Read/Write/Forget. Gated Recurrent Unit (GRU). |
06 | Recent Trends & Applications | Generative Adversarial Network (GAN): Architecture. Applications: Image Generation, DeepFake. |
Prof. S. M. Patil, SIGCE, Department of AI & DS
Text Books
1. Ian Goodfellow, Yoshua Bengio, Aaron Courville. "Deep Learning", MIT Press Ltd, 2016.
�2. Li Deng and Dong Yu. "Deep Learning Methods and Applications", Publishers Inc.
�3. Satish Kumar. "Neural Networks: A Classroom Approach", Tata McGraw-Hill.�
4. JM Zurada. "Introduction to Artificial Neural Systems", Jaico Publishing House.�
5. M. J. Kochenderfer, Tim A. Wheeler. "Algorithms for Optimization", MIT Press.
Prof. S. M. Patil, SIGCE, Department of AI & DS
Reference Books:
1. Seth Weidman. "Deep Learning from Scratch: Building with Python from First Principles", O'Reilly.
�2. Francois Chollet. "Deep learning with Python" (Vol. 361). Manning, 2018.�
3. Douwe Osinga. "Deep Learning Cookbook", O'REILLY, SPD Publishers, Delhi.
�4. Simon Haykin. "Neural Network: A Comprehensive Foundation", Prentice Hall International.�
5. S.N. Sivanandam and S.N. Deepa. "Principles of Soft Computing", Wiley India.
Prof. S. M. Patil, SIGCE, Department of AI & DS
Unit Test I & II Structure
Questions | | Marks | Unit Test I | Unit Test II |
1 | a | 5 | CO1 | CO4 |
OR | b | 5 | CO1 | CO4 |
2 | a | 5 | CO2 | CO5 |
OR | b | 5 | CO2 | CO5 |
3 | a | 5 | CO3 | CO6 |
OR | b | 5 | CO3 | CO6 |
Prof. S. M. Patil, SIGCE, Department of AI & DS
Term Test Question Paper Analysis
Module No. | No. of Hours x | Total Credit Assigned y=39, z=3 | Total Marks Assigned (x*Q)/y Q=32 | % of Weightage (x*100/y) | Term Test Q Paper Actually Mark Allotted | % of Weightage 2023-24 |
1 | 4 | 0.31 | 3 | 10 | | |
2 | 10 | 0.77 | 8 | 26 | | |
3 | 6 | 0.46 | 5 | 15 | | |
Total | 20 | 1.54 | 16 | 51% | | |
4 | 7 | 0.54 | 5.8 | 18 | | |
5 | 8 | 0.62 | 6.5 | 21 | | |
6 | 4 | 0.31 | 3 | 10 | | |
Total | 19 | 1.46 | 15.3 | 49% | | |
Prof. S. M. Patil, SIGCE, Department of AI & DS
Thanks
Prof. S. M. Patil, SIGCE, Department of AI & DS