Scribd
Upload
34 views2 pages

Deep Learning Assignments 02

The document is an assignment for a course on Deep Learning Essentials, consisting of three questions related to learning rate scheduling, computation graphs in backpropagation, and applications of fully connected neural networks. Each question requires a detailed response of 150-200 words, with grading criteria based on accuracy, clarity, research, and originality. The total assignment is worth 30 marks, with each question contributing 10 marks.

Uploaded by

angularmotionam1122
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
34 views2 pages

Deep Learning Assignments 02

The document is an assignment for a course on Deep Learning Essentials, consisting of three questions related to learning rate scheduling, computation graphs in backpropagation, and applications of fully connected neural networks. Each question requires a detailed response of 150-200 words, with grading criteria based on accuracy, clarity, research, and originality. The total assignment is worth 30 marks, with each question contributing 10 marks.

Uploaded by

angularmotionam1122
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

Assignment 02

Deep Learning Essentials

Instructions:​
Answer the following questions based on the concepts covered in the lectures. Use
external resources to research (i.e. Google) to explore and expand your
understanding. Each question should be answered in 150–200 words.

Question 1: Learning Rate Scheduling in Gradient Descent

In the lecture on Gradient Descent, we learned about the importance of the


learning rate in optimizing neural networks. However, using a fixed learning rate
can sometimes lead to suboptimal results. Research and describe two learning
rate scheduling techniques (e.g., Learning Rate Decay, Cyclical Learning Rates, or
Step Decay). Explain how these techniques adjust the learning rate during training,
their benefits, and in what scenarios they are most effective.

Question 2: The Role of Computation Graphs in Backpropagation

The lecture on Forward and Backward Propagation introduced computation graphs


as a way to visualize the flow of calculations in neural networks. Research and
explain how computation graphs are used in backpropagation to calculate
gradients efficiently. Provide an example of a simple computation graph e.g., for a
function like
f(x,y)=x⋅y+z
and show how gradients are computed using the chain rule.

Question 3: Applications of Fully Connected Neural Networks

In the lecture on Fully Connected Neural Networks (FCNNs), we discussed their


structure and basic applications. However, FCNNs are used in many advanced
real-world applications. Research and describe two advanced applications of
FCNNs (e.g., medical diagnosis, autonomous driving, or recommendation systems).
Explain how FCNNs are adapted to handle the specific challenges of these
applications and what makes them suitable for these tasks.

Grading Criteria

Each question is worth 10 marks, and the assignment is graded out of a total of 30
marks. The grading will be based on the following criteria:
1.​ Accuracy and Depth of Explanation (4 marks):
○​ The answer should accurately explain the concepts and provide
sufficient depth.
○​ Use of relevant examples or applications to support the explanation.
2.​ Clarity and Organization (3 marks):
○​ The answer should be well-structured, clear, and easy to follow.
○​ Proper use of paragraphs, headings, and bullet points (if applicable).
3.​ Research and Exploration (2 marks):
○​ Evidence of research beyond the lecture content.
○​ Use of credible external resources to enhance the explanation.
4.​ Originality and Reflection (1 mark):
○​ The answer should demonstrate original thought and personal
reflection.
○​ Avoid copying directly from sources; paraphrase and synthesize
information.
Total Marks: 30
●​ Question 1: 10 marks
●​ Question 2: 10 marks
●​ Question 3: 10 marks

Good luck!

You might also like