标签:education
带有 education 标签的公开 Whisper
划选高亮2026-08-11 18:38:48
原文高亮摘录
“a comparison sort cannot perform better than O(n log n) on average”
Whisper 随想笔记
So that's why my custom sort is always slower than the built-in.
划选高亮2026-08-11 12:32:48
原文高亮摘录
“the output of any sorting algorithm must satisfy two conditions”
Whisper 随想笔记
Even the definition sounds like a math test I'd fail.
划选高亮2026-08-11 12:14:48
原文高亮摘录
“the output of any sorting algorithm must satisfy two conditions”
Whisper 随想笔记
Two conditions? I thought it was just 'small to big' and done.
划选高亮2026-08-09 16:32:41
原文高亮摘录
“In a well-dimensioned hash table, the average time complexity for each lookup is independent of the number of elements stored”
Whisper 随想笔记
Average is the key word—worst case is still a nightmare though.
划选高亮2026-08-08 15:09:57
原文高亮摘录
“The term machine learning was coined in 1959 by Arthur Samuel”
Whisper 随想笔记
Arthur Samuel coined the term way back in 1959, that's wild.
划选高亮2026-07-28 16:11:42
原文高亮摘录
“Move semantics enable the transfer of resources and ownership between objects”
Whisper 随想笔记
This is exactly why modern C++ feels so much safer than the old pointer juggling days.
划选高亮2026-07-28 13:24:57
原文高亮摘录
“The simplest way to perform the copying task perfectly would be to duplicate the signal.”
Whisper 随想笔记
Duplicating the signal defeats the whole purpose, obviously.
划选高亮2026-07-28 12:52:34
原文高亮摘录
“Content-based filtering methods are based on a description of the item and a profile of the user's preferences”
Whisper 随想笔记
So basically it just matches what you liked before with similar stuff, right?
划选高亮2026-07-28 10:11:53
原文高亮摘录
“A typical generative task is as follows. At each step, a datapoint is sampled from the dataset, and part of the data is removed, and the model must infer the removed part.”
Whisper 随想笔记
That's how they train those language models? Seems almost too simple to work that well.
划选高亮2026-07-27 13:23:48
原文高亮摘录
“The main difference between federated learning and distributed learning lies in the assumptions made on the properties of the local datasets”
Whisper 随想笔记
Huh, I always thought they were the same thing. This clears it up a bit.
划选高亮2026-07-27 13:15:52
原文高亮摘录
“The key design element of GNNs is the use of pairwise message passing”
Whisper 随想笔记
So the whole GNN thing really just boils down to neighbors chatting with each other, huh?
划选高亮2026-07-27 13:14:48
原文高亮摘录
“The main difference between federated learning and distributed learning lies in the assumptions made on the properties of the local datasets”
Whisper 随想笔记
So it's basically about who owns the data and how messy it is, got it.
划选高亮2026-07-27 10:03:52
原文高亮摘录
“Graph neural networks (GNNs) are artificial neural networks designed for tasks whose inputs are graphs.”
Whisper 随想笔记
So basically they made neural nets that can handle family trees and stuff?
划选高亮2026-07-27 09:47:37
原文高亮摘录
“Aggregate functions compute a single result from a set of input values.”
Whisper 随想笔记
So basically it's just like SUM or AVG but for any set of values, got it.
划选高亮2026-07-27 09:37:15
原文高亮摘录
“A module is a file containing Python definitions and statements.”
Whisper 随想笔记
I always wondered why __name__ showed up in scripts. Now it makes sense.
划选高亮2026-07-27 09:19:15
原文高亮摘录
“A module is a file containing Python definitions and statements.”
Whisper 随想笔记
So basically any .py file is a module? That's simpler than I thought.
划选高亮2026-07-26 16:27:45
原文高亮摘录
“The autocorrelation function of an AR(p) process is a sum of decaying exponentials.”
Whisper 随想笔记
So basically the memory fades out smoothly, like echoes getting quieter.
划选高亮2026-07-26 16:11:31
原文高亮摘录
“A policy is a rule used by an agent to decide what actions to take.”
Whisper 随想笔记
So basically it's just the brain of the agent, got it.
划选高亮2026-07-26 15:43:07
原文高亮摘录
“Assignments do not copy data — they just bind names to objects.”
Whisper 随想笔记
So that's why my list changes when I pass it to a function and modify it inside... makes sense now.
划选高亮2026-07-26 13:24:45
原文高亮摘录
“Large language models are called autoregressive, but they are not a classical autoregressive model in this sense because they are not linear.”
Whisper 随想笔记
Wait, I thought autoregressive just meant predicting the next word, why the linear caveat?