Scribd
Upload
6 views1 page

Deep Learning Assignment for B.Tech AI/DS

The document is an assignment for the 6th semester B. Tech students in Artificial Intelligence and Data Science at CGC College of Engineering, focusing on Deep Learning. It outlines course outcomes related to advancements in AI, deep learning architectures, and practical applications of neural networks, with specific questions assigned for evaluation. The assignment is to be submitted by October 15, 2025, and includes various tasks aligned with Bloom's Taxonomy levels.

Uploaded by

avneesh.6070
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views1 page

Deep Learning Assignment for B.Tech AI/DS

The document is an assignment for the 6th semester B. Tech students in Artificial Intelligence and Data Science at CGC College of Engineering, focusing on Deep Learning. It outlines course outcomes related to advancements in AI, deep learning architectures, and practical applications of neural networks, with specific questions assigned for evaluation. The assignment is to be submitted by October 15, 2025, and includes various tasks aligned with Bloom's Taxonomy levels.

Uploaded by

avneesh.6070
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

CGC College of Engineering

Landran, Mohali, Punjab

Ref. No. COE/CSE/IQAC/2024-25/

Department of Computer Science & Engineering

Reappear Assignment
Total Marks-10
Branch: B. Tech (Artificial intelligence and Data Science)
Subject & Subject code: Deep Learning (BTCS 704-18)
Semester: 6th
Date on which assignment is given: 04/10/2025 Date of submission of assignment: 15/10/2025

Course Outcomes:
CO1 Analyze the advancements in learning techniques and their impact on modern AI systems.

CO2 Evaluate and differentiate various deep learning architectures and algorithms based on their functionalities.

CO3 Demonstrate practical applications of Convolutional Neural Networks in solving computer vision problems.

CO4 Implement Recurrent Neural Networks for effective sequence modeling in time-series and natural language tasks.

CO5 Design and deploy Deep Generative Models for creating and synthesizing data across different domains.

Bloom’s Taxonomy Levels


L1 – Remembering, L2 – Understanding, L3 – Applying, L4 – Analyzing, L5 – Evaluating, L6 - Creating

Relevance to Bloom's
Assignment related to COs Marks
CO No. Levels
Q1. Distinguish different machine learning algorithms. 2 CO1 L4
Define the following terms:
(i) Maximum Likelihood Estimation
Q2. (ii) Bias & Variance 2 CO1 L1
(iii) Underfitting & Over-fitting
(iv) Data Augmentation
Q3. Explain feed forward neural networks with suitable
2 CO2 L2
example.
Compare the effects of different pooling strategies (max
Q4. 2 CO3 L4
pooling vs. average pooling) on feature extraction.
Q5. Explain how contrastive divergence is used in training
2 CO5 L2
Restricted Boltzmann Machines.

You might also like