[GH-ISSUE #417] Notes In "ondevice_learning.qmd" #1418

New Issue

GiteaMirror · 2026-04-11T07:48:31-05:00

GiteaMirror commented

2026-04-11 07:48:31 -05:00

Originally created by @BravoBaldo on GitHub (Aug 28, 2024).
Original GitHub issue: https://github.com/harvard-edge/cs249r_book/issues/417

In "ondevice_learning.qmd":

Section "Regulatory Compliance", "...like (GDPR) and CCPA."---> Why only one in brackets?
Sub-section "Dataset Size, Accuracy, and Generalization": "Withel's real-world"... ???
Search "Traditional cloud-based DNN"... duplicated paragraph
"The server then updates the server with"... (duplicated "server")
"Further DESCRIPTION of specific aggregation algorithms is DESCRIBED by" -->(suggestion) "Further specific aggregation algorithms are described by"
"and inform the chatbot's responses." (??? inform ???)
"In the example you mentioned" ... you who?
Please review "Table 12.3: Comparison of frameworks for on-device training optimization." it is badly formatted!!!
Please search "The emergence of specialized on-device training frameworks like" and review the phrase.
Suggestion:
- From: Quantization-aware training: In this step, the neural network is trained with quantization in mind, using simulated quantization to mimic the effects of quantization during the forward and backward passes.
- To: Quantization-aware training: In this step, the neural network is trained with quantization in mind, simulating it to mimic its effects during forward and backward passes.

Baldo

Originally created by @BravoBaldo on GitHub (Aug 28, 2024). Original GitHub issue: https://github.com/harvard-edge/cs249r_book/issues/417 In "ondevice_learning.qmd": - Section "Regulatory Compliance", "...like (GDPR) and CCPA."---> Why only one in brackets? - Sub-section "Dataset Size, Accuracy, and Generalization": "Withel's real-world"... ??? - Search "Traditional cloud-based DNN"... duplicated paragraph - "The server then updates the server with"... (duplicated "server") - "Further DESCRIPTION of specific aggregation algorithms is DESCRIBED by" -->(suggestion) "Further specific aggregation algorithms are described by" - "and inform the chatbot's responses." (??? inform ???) - "In the example you mentioned" ... you who? - Please review "Table 12.3: Comparison of frameworks for on-device training optimization." it is badly formatted!!! - Please search "The emergence of specialized on-device training frameworks like" and review the phrase. - Suggestion: - From: Quantization-aware training: In this step, the neural network is trained with quantization in mind, using simulated quantization to mimic the effects of quantization during the forward and backward passes. - To: Quantization-aware training: In this step, the neural network is trained with quantization in mind, simulating it to mimic its effects during forward and backward passes. Baldo

GiteaMirror added the area: book label 2026-04-11 07:48:31 -05:00

GiteaMirror closed this issue

2026-04-11 07:48:32 -05:00

GiteaMirror referenced this issue

2026-04-21 22:24:06 -05:00

[PR #1418] [MERGED] fix(publish): block silent version downgrades in tinytorch + book publish-live #6537

GiteaMirror referenced this issue

2026-04-27 17:29:18 -05:00

[PR #1418] [MERGED] fix(publish): block silent version downgrades in tinytorch + book publish-live #8184

GiteaMirror referenced this issue

2026-05-03 01:19:44 -05:00

[PR #1418] [MERGED] fix(publish): block silent version downgrades in tinytorch + book publish-live #9089