Scribd
Upload
127 views3 pages

VIT Vellore Deep Learning Syllabus 2024

The VIT autonomous curriculum for the Deep Learning course consists of 6 buckets, with the course included in the Program Core Courses requiring a minimum of 80 credits, of which around 66 credits have been completed by students. The course has prerequisites in Applied Mathematics, Machine Learning, and Soft Computing, and covers topics such as Neural Networks and Deep Neural Networks, with applications in image classification and financial forecasting. Evaluation includes theory and practical components, with a total of 30 lecture hours planned and resources available for students.

Uploaded by

siddharthchavan071
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
127 views3 pages

VIT Vellore Deep Learning Syllabus 2024

The VIT autonomous curriculum for the Deep Learning course consists of 6 buckets, with the course included in the Program Core Courses requiring a minimum of 80 credits, of which around 66 credits have been completed by students. The course has prerequisites in Applied Mathematics, Machine Learning, and Soft Computing, and covers topics such as Neural Networks and Deep Neural Networks, with applications in image classification and financial forecasting. Evaluation includes theory and practical components, with a total of 30 lecture hours planned and resources available for students.

Uploaded by

siddharthchavan071
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Assignment – 0: Deep Learning

Q1.a How many buckets are there in the VIT autonomous curriculum (syllabus)?
→ 6 buckets:

 BSC/ESC

 Program Core Courses

 Multidisciplinary Courses

 Skill Courses

 HSSM

 Experiential & Liberal Learning

Q1.b In which bucket is this course included?


→ Program Core Courses

Q1.c How many credits need to be completed from this bucket?


→ Minimum 80 credits

Q1.d How many credits from this bucket have you completed till now?
→ Around 66 credits (may vary per student)

Q1.e How many credits does this course have?


→ 4 credits total (2 theory + 2 practical)

Q2.a Have you gone through the curriculum of your course?


→ Yes

Q2.b Is there a pre-requisite for this course?


→ Yes – Applied Mathematics (Statistics), Machine Learning (ANN), Soft Computing (MLP)

Q2.c Do you remember the concepts of the pre-requisite courses?


→ Mostly yes, but a quick review will help

Q2.d Preparations needed for this course:


→ Revise linear algebra/statistics, basics of ANNs and MLPs; install Python, TensorFlow, PyTorch, Keras

Q2.e Future courses that build on this course:


→ Project I (Sem 7), Social Media Analytics (Sem 8), Project II (Sem 8)

Q3.a List of Course Outcomes (COs):

 CO1: Basics of Neural Networks

 CO2: In-depth training of Deep Neural Networks


 CO3: Designing DNN models for supervised, unsupervised & sequence tasks

 CO4: Familiarity with recent trends & applications in Deep Learning

→ Most useful: CO4

Q3.b How are these COs mapped to POs?


→ Mapped as per AAP Table (e.g., CO1 → PO1: Strong, PO2: Moderate)

Q4 Where do you see the applications of this course?


→ Image classification & object detection, anomaly detection (fraud), deepfake generation/detection, robotics &
Game AI, financial forecasting

Q5.a One top university with a similar course:


→ Stanford University – CS230: Deep Learning

Q5.b How does their curriculum compare with ours?


→ Stanford’s CS230 emphasizes theoretical foundations and extensive coding assignments; our course covers
core NN concepts, hands-on labs across CNNs, RNNs, GANs & RL with practical projects.

Q6.a How many lecture sessions are planned?


→ 30 hours total

Q6.b Suggested textbooks and references:

 Goodfellow et al., Deep Learning (MIT Press) – All modules (available)

 Deng & Yu, Deep Learning Methods & Applications – Modules 3–4 (available)

 Kumar, Neural Networks: A Classroom Approach – Modules 1–4 (available)

Q6.c Resources on V-refer:


→ Syllabus, AAP, Lecture Guide, Assignments

Q6.d Faculty office hours:


→ Friday 3:45 PM – 4:45 PM (Room L-12)

Q7.a Evaluation metric (Theory):


→ ISA: 15, MSE: 20, ESE: 40 → Total: 75 marks

Q7.b What does ISA include?


→ Assignments, tutorials/quizzes, class activities

Q7.c ISA rubric:


→ Each activity/tutorial: 10 marks; class participation also counted
Q7.d MSE dates:
→ MSE-1: Week 4, MSE-2: Week 8

Q7.e ESE date:


→ December 2025 (tentative)

Q8.a Is there an allied practical course?


→ Yes – EC37P: Deep Learning Lab

Q8.b Credits for practical course:


→ 2 credits

Q8.c Evaluation for practical course:


→ ISA: 25, ESE: 25 → Total: 50 marks

Q8.d ESE for practical:


→ December 2025

Q9 Date of result declaration:


→ January 2026

Q10 Start of next academic term:


→ January 2026

You might also like