[GH-ISSUE #315] Student Feedback - Chapter Three #3979

New Issue

GiteaMirror · 2026-04-19T12:01:53-05:00

GiteaMirror commented

2026-04-19 12:01:53 -05:00

Originally created by @jasonjabbour on GitHub (Jul 15, 2024).
Original GitHub issue: https://github.com/harvard-edge/cs249r_book/issues/315

Originally assigned to: @jasonjabbour on GitHub.

Chapter Three - DL Primer

In 3.2 Neural Networks, we feel like we would've benefitted from more detail about weights, biases, and activation functions used by a Perceptron to create an output.
In 3.2.2 Multilayer Perceptron section, we didn't fully understand the concept of layers until we watched the included videos. If students are intended to understand these ideas without help from video, perhaps go into more detail?
After reading the Backpropagation section, we still found ourselves confused about how this algorithm benefits deep neural networks
We wish there was more detail in the CNN section. Specifically, how are CNNs different from multilayer perceptrons?
In 3.2.5 Choosing Traditional ML vs DL, we were under the assumption that deep learning is a kind of ML. Could you clarify this in the text?

Machine Learning Systems - 3 DL Primer.pdf

Originally posted by @sgiannuzzi39 in https://github.com/harvard-edge/cs249r_book/discussions/256#discussioncomment-9729854

Originally created by @jasonjabbour on GitHub (Jul 15, 2024). Original GitHub issue: https://github.com/harvard-edge/cs249r_book/issues/315 Originally assigned to: @jasonjabbour on GitHub. ### **Chapter Three - DL Primer** - In **3.2 Neural Networks**, we feel like we would've benefitted from more detail about weights, biases, and activation functions used by a Perceptron to create an output. - In **3.2.2 Multilayer Perceptron** section, we didn't fully understand the concept of layers until we watched the included videos. If students are intended to understand these ideas without help from video, perhaps go into more detail? - After reading the Backpropagation section, we still found ourselves confused about how this algorithm benefits deep neural networks - We wish there was more detail in the CNN section. Specifically, how are CNNs different from multilayer perceptrons? - In **3.2.5 Choosing Traditional ML vs DL**, we were under the assumption that deep learning is a kind of ML. Could you clarify this in the text? [Machine Learning Systems - 3 DL Primer.pdf](https://github.com/user-attachments/files/15776693/Machine.Learning.Systems.-.3.DL.Primer.pdf) _Originally posted by @sgiannuzzi39 in https://github.com/harvard-edge/cs249r_book/discussions/256#discussioncomment-9729854_

GiteaMirror added the area: book type: improvement labels 2026-04-19 12:01:53 -05:00

GiteaMirror closed this issue

2026-04-19 12:01:54 -05:00

GiteaMirror commented

2026-04-19 12:01:56 -05:00

@jasonjabbour commented on GitHub (Jul 15, 2024):

Add more details about weights, biases, and activation functions.
Explain the concept of layers in neural networks.
Better motivate the need for backpropagation and how it fits into the training process.
Better distinguish CNNs from MLPs.
Clarify difference between what we mean by traditional ML and DL.

@jasonjabbour commented on GitHub (Jul 15, 2024): - [x] Add more details about weights, biases, and activation functions. - [x] Explain the concept of layers in neural networks. - [x] Better motivate the need for backpropagation and how it fits into the training process. - [x] Better distinguish CNNs from MLPs. - [x] Clarify difference between what we mean by traditional ML and DL.

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/cs249r_book#3979