于式瘋情 (Crazy Bits with Yu)

[BitOfCS] [資料結構] 堆疊跟佇列差在哪？人生就是一個 Stack：總是在後悔。進出順序決定一切(含互動視覺化網站) Stack & Queue. Life Is a Stack — Always Undoing Mistakes. It's All About Who Gets In and Out First (Interactive Website)

YuYu — Wed, 20 May 2026 02:52:21 GMT

🌐 互動視覺化網站 Interactive Website
邊看邊玩，自己動手。Try it yourself — visualize everything!
👉 https://sanasana0308.github.io/ds-algo/

你有沒有想過，為什麼 Ctrl+Z 可以救你？為什麼印表機不會插隊？為什麼 LINE 訊息按照順序來？答案都在這兩個資料結構裡：Stack（堆疊）和 Queue（佇列）。
「反正這兩個不就是放進去拿出來？」一句話差點讓你錯過最核心的差異。這集從生活例子出發，帶你理解兩者最核心的差異：LIFO（後進先出）vs FIFO（先進先出），搭配互動視覺化網站用 push、pop、enqueue、dequeue 模擬資料進出。學完之後你會後悔以前怎麼都不知道——然後立刻想 Ctrl+Z 回去重讀。
Ever wonder why Ctrl+Z saves your life, why the printer respects first-come-first-served, or why LINE messages show up in order? Blame Stack and Queue.
"Aren't they basically the same — just put things in and take things out?" That one assumption will cost you the exam.
This video breaks down the key difference between LIFO and FIFO using relatable real-world examples, then walks through hands-on exercises with push, pop, enqueue, and dequeue operations.
There will be a moment where you want to Ctrl+Z your entire CS education. You've been warned.

#資料結構 #Stack #Queue #堆疊 #佇列 #LIFO #FIFO #push #pop #演算法 #演算法入門 #ctrlz #資訊科學 #程式設計 #程式觀念 #CS入門 #DataStructure #StackAndQueue #StackVsQueue #LIFOvsFIFO #DataStructures #DataStructuresTutorial #ComputerScienceBasics #CodingForBeginners #LearnToCode #AI時代學程式 #CrazyBitWithYu #于式瘋情

--
Hosting provided by SoundOn

[BitOfCS] [資料結構] 陣列鏈結串列(2互動視覺化網站)。你每天都在用，卻從來沒注意過的資料結構 The Data Structures You Use Every Day (Without Knowing It) (2: Interactive Data Visualization Website)

YuYu — Thu, 14 May 2026 08:24:29 GMT

互動視覺化網站 Interactive Data Visualization Website
** [https://sanasana0308.github.io/ds-algo/**](< https://sanasana0308.github.io/ds-algo/>)>)

陣列、鏈結串列根本不一樣，讓你再也不搞混
Array vs Linked List — Stop Confusing Them Forever

你每天滑 YouTube、用 Google 搜尋，背後默默運作的就是資料結構。
「反正都用陣列就好了吧？」——這句話讓無數程式跑慢了一輩子。
如果你的書房是一片混亂，你找一本書可能要翻半小時；但如果你有書架、有分類，三秒就找到。這就是資料結構在做的事。
這集我們用最接地氣的方式，把陣列（Array）跟鏈結串列（Linked List）的差異講清楚：讀取誰快、插入誰贏、記憶體誰省。

#資料結構 #Array #陣列 #LinkedList #鏈結串列 #BigO #複雜度分析 #RandomAccess #指標 #Pointer #CS入門 #程式開發基礎 #Array #陣列 #LinkedList #鏈結串列 #BigO #DataStructure #ArrayVsLinkedList #AI時代學程式 #Index #索引 #Pointer #指標 #LearnToCode #ComputerScienceBasics
--
Hosting provided by SoundOn

[BitOfCS] [資料結構] 陣列鏈結串列(1:理論)。你每天都在用，卻從來沒注意過的資料結構。[Data Structure] Array Linked List. The Data Structures Every Day (1: theory)

YuYu — Mon, 11 May 2026 08:41:56 GMT

你每天滑 YouTube、用 Google 搜尋，背後默默運作的就是資料結構。
「反正都用陣列就好了吧？」——這句話讓無數程式跑慢了一輩子。
如果你的書房是一片混亂，你找一本書可能要翻半小時；但如果你有書架、有分類，三秒就找到。這就是資料結構在做的事。
這集我們用最接地氣的方式，把陣列（Array）跟鏈結串列（Linked List）的差異講清楚：讀取誰快、插入誰贏、記憶體誰省。
#資料結構 #Array #陣列 #LinkedList #鏈結串列 #BigO #複雜度分析 #RandomAccess #指標 #Pointer #CS入門 #程式開發基礎 #Array #陣列 #LinkedList #鏈結串列 #BigO #DataStructure #ArrayVsLinkedList #AI時代學程式 #Index #索引 #Pointer #指標 #LearnToCode #ComputerScienceBasics
--
Hosting provided by SoundOn

[BitOfAI] [細說Transformer] QKV & self-attention(上) | chatGPT怎麼知道蘋果到底是水果還是公司？Transformer 的靈魂：QKV 與自注意力機制。

YuYu — Thu, 30 Apr 2026 08:50:57 GMT

電腦怎麼知道你說的「蘋果」能不能吃？這部影片將帶你深入 Transformer 的核心——Self-Attention（自注意力機制）。我們將把枯燥的數學轉化為好懂的「角色扮演」，介紹 AI 理解語言的三大祕密武器：

Q (Query) 發問者：我在哪？誰跟我有關？
K (Key) 資訊提供者：標籤化特徵，對應發問者的需求。
V (Value) 真實內涵：字典裡的具體語義。透過向量投影與矩陣運算，AI 能像擁有「上帝視角」一樣觀察前後文，精準修正詞彙的座標，徹底解決一詞多義的難題！

English Description: How does a computer know if the "Apple" you're mentioning is edible? This video dives into the heart of Transformers: Self-Attention. We transform dry mathematics into an easy-to-understand "role-play," introducing AI's three secret weapons for language understanding:

Q (Query): The Questioner – "Where am I? Who is relevant to me?"
K (Key): The Info Provider – Tagging features to match queries.
V (Value): The Real Content – The specific dictionary definition. Through vector projection and matrix multiplication, AI gains a "God's eye view" of the context, precisely adjusting word coordinates to solve the puzzle of polysemy!

--
Hosting provided by SoundOn

[BitOfAI] 從 Token 到向量：AI怎麼看懂我們的語言? 教它把「蘋果」轉成數學座標！ From Token to Vector: How does AI Understand Human’s Language?

YuYu — Thu, 23 Apr 2026 06:37:33 GMT

別再對電腦說人話了，它只聽得懂「中括號」裡的向量祕密。AI 其實是個只懂數學的「三歲小孩」！它看不懂中文，在它眼裡，你的情書或簡訊全是一堆數字。

Token：依照token數收費就是它！看 AI 如何把句子切成它才懂的小方塊,。
512 維的神祕空間：文字變身「向量」，連「高貴感」都能化為座標,。
內積大運算：用數學算出「蘋果」跟「手機」到底有多像？。
Attention 注意力：看 AI 如何動態判斷你買的是水果還是新手機！

想知道你的文字在 AI 座標軸裡長什麼樣子？點進來，一起把語言變成超酷的數學地圖！

AI is basically a math-obsessed 3-year-old! It doesn't read words; it processes numbers.

Token Slicing: How sentences are broken into bite-sized units for the model,.
The 512-Dimension Map: Turning words into "vectors" where even a "fancy vibe" has its own coordinate,.
Dot Product Magic: Calculating exactly how close an "Apple" is to a "Smartphone" using math.
Attention Please!: How AI dynamically tells if you're eating an Apple or calling from one!

Curious how your words look in a multi-dimensional universe? Let’s turn language into a cool mathematical map!
#tokenization , #WordEmbedding #dotproduct #transformer #Word2Vec. #AI #人工智慧 #Token#分詞 #維度 #內積 #注意力機制 #nlp #AIVernacular #AI白話文 #電腦如何理解語言
--
Hosting provided by SoundOn

[BitOfAI] AI本質是函數 | (類)神經網路的老派浪漫(下) - The Essence of AI is a Function: The "Old-School Romance" of Neural Networks

YuYu — Thu, 16 Apr 2026 08:18:36 GMT

分清「貴賓狗還炸雞」也可 f(x)嗎?
雖然當紅的是「生成式 AI」，但其核心底層始終是「(類)神經網路」，很多人會跳過神經網路，還來不及了解"傳統AI"在做什麼，就直接學習當紅酷炫的"生成式AI"理論。這就像在不穩固的地基上蓋房子，其實是有點可惜且危險的。

從基礎的「辨識」任務(例如分清貴賓狗還是炸雞！)，到先進的「生成」任務，這是一脈相承的技術演進。本影片帶大家回到原點，理解AI如何從神經網路找出完美的f(x)函數。

AI的理論世界豐富且各具風情，鼓勵大家先從簡單的神經網路扎根，在往後探索LLM或Transformer的奧秘。讓我們一起享受探索學習的樂趣吧！　：Ｄ

Can Distinguishing "Poodle or Fried Chicken" be f(x), too?
Neural Networks are the essential foundation of everything we see in AI today. Nowadays, it’s tempting to jump straight into the flashy world of Generative AI, but skipping the "Traditional AI" basics is like trying to build a skyscraper on a shaky foundation.
The journey from "Recognition" (like telling a poodle from fried chicken!) to "Generation" (creating something brand new) is a continuous path of learning. In this video, we go back to the roots to understand how AI finds the perfect f(x) function through neural networks.
AI theory is a vast and beautiful landscape with many different "flavors." I encourage everyone to master the simple basics of neural networks first before diving deeper into the wonders of LLMs and Transformers. Let’s explore this amazing world of learning together!

#genai #ai #neuralnetworks #function #fofx #llm #crazybitwithyu #transformer #poodle #friedchicken
--
Hosting provided by SoundOn

[BitOfAI] AI本質是函數 | (類)神經網路的老派浪漫(上) - The Essence of AI is a Function: The "Old-School Romance" of Neural Networks

YuYu — Fri, 10 Apr 2026 03:24:05 GMT

分清「貴賓狗還炸雞」也可 f(x)嗎?
雖然當紅的是「生成式 AI」，但其核心底層始終是「(類)神經網路」，很多人會跳過神經網路，還來不及了解"傳統AI"在做什麼，就直接學習當紅酷炫的"生成式AI"理論。這就像在不穩固的地基上蓋房子，其實是有點可惜且危險的。

從基礎的「辨識」任務(例如分清貴賓狗還是炸雞！)，到先進的「生成」任務，這是一脈相承的技術演進。本影片帶大家回到原點，理解AI如何從神經網路找出完美的f(x)函數。

AI的理論世界豐富且各具風情，鼓勵大家先從簡單的神經網路扎根，在往後探索LLM或Transformer的奧秘。讓我們一起享受探索學習的樂趣吧！　：Ｄ

Can Distinguishing "Poodle or Fried Chicken" be f(x), too?
Neural Networks are the essential foundation of everything we see in AI today. Nowadays, it’s tempting to jump straight into the flashy world of Generative AI, but skipping the "Traditional AI" basics is like trying to build a skyscraper on a shaky foundation.
The journey from "Recognition" (like telling a poodle from fried chicken!) to "Generation" (creating something brand new) is a continuous path of learning. In this video, we go back to the roots to understand how AI finds the perfect f(x) function through neural networks.
AI theory is a vast and beautiful landscape with many different "flavors." I encourage everyone to master the simple basics of neural networks first before diving deeper into the wonders of LLMs and Transformers. Let’s explore this amazing world of learning together!

#genai #ai #neuralnetworks #function #fofx #llm #crazybitwithyu #transformer #poodle #friedchicken
--
Hosting provided by SoundOn

[BitOfAI] 速講RNN & Transformer | LLM只是文字接龍嗎? Transformer: 那些RNN不能解決的就交給我吧。| Is LLM only text continuation? Transformer: Let me solve what RNN cannot solve.

YuYu — Tue, 31 Mar 2026 08:08:32 GMT

[A Bit of Tech] 速講 LLM RNN Transformer | LLM只是文字接龍嗎? 我只是想要被理解。Transformer: 那些RNN不能解決的就交給我吧。
很多人說 LLM只是文字接龍，你覺得呢?
我只是想要被理解，如果是的話我該怎麼辦?
RNN(循環神經網路)作為神經網路三大巨頭之一，他也有不行的時候。
因此Transformer發下狂語說: 「All you need is attention.」那些RNN不能解決的就交給我吧。

Many people say that LLMs are just doing text continuation.
What do you think?
Sometimes a sentence like this appears:“I just want to be understood. If that’s the case, what should I do?”

Even RNNs (Recurrent Neural Networks) — one of the three major types of neural networks — have situations where they struggle.
Then Transformer came along and boldly declared:“All you need is attention.”
The problems that RNNs cannot solve? Leave them to me.

#llm #ai #transformer #selfattention #neuralnetworks #rnn #largelanguagemodels #crazybitwithyu
--
Hosting provided by SoundOn

[BitOfCreate] 我不知道主題做什麼啊? | 先發想再建置，你的AI chatbot. - What the topic should be about? | Think first then build up.

YuYu — Fri, 27 Mar 2026 02:45:47 GMT

建立一個小chatbot，是學習AI agent很棒的起點。
很多人會說有了AI的幫忙，技術不再是問題，但我不知道主題要做什麼啊?
確實技術不再是問題了，但必須在一開始就做好發想的準備和練習，好好地創造，想清楚why and what，天馬行空的瘋狂想像一番，有計畫的制定每個步驟，創意和想法才是最重要的第一步。

If AI makes a mistake, call it a 'Beta test'; if you make a mistake, call it an 'Artistic choice'.
Keep dreaming big and stay legendary! :)
--
Hosting provided by SoundOn