關於
Stephen Welch is the creator of Welch Labs, a YouTube channel that explains AI, mathematics and science through animation rather than conversation. He started it in 2014, frustrated with the material available on neural networks, by making his own: Neural Networks Demystified, a short series that builds and trains a network in Python. He holds engineering degrees from Georgia Tech and UC Berkeley, led deep-learning vision work for driver-assistance and autonomous products as VP of Machine Learning at Autonomous Fusion, and has taught computer vision at UNC Charlotte. He ran the channel on the side for a decade before going full time, and loved math as a child but fell out of love with it in college — he blames the teaching, not the subject, and the channel is his answer to it.
主要貢獻
- Started Welch Labs in 2014 with Neural Networks Demystified, building and training a complete neural network in Python on screen
- Made Imaginary Numbers Are Real, the channel's most successful series, and published it as a book
- Wrote The Welch Labs Illustrated Guide to AI (2025), a 376-page first volume running from the perceptron to AI video generation, with code and exercises
- Led a team building deep-learning vision for driver-assistance and autonomous products as VP of Machine Learning at Autonomous Fusion
- His videos in this collection draw the arguments other channels talk through: AlexNet and the moment we stopped understanding AI, the compute-optimal frontier, sparse autoencoders, LeCun's JEPA, and why gradient descent does not get stuck
主持過的 6 場對話
思想連結
Grant Sanderson
曾經合作數學家與教育者（3Blue1Brown）
2025 年夏天，Sanderson 把自己的頻道交給了 Welch：3Blue1Brown 那支講解擴散模型究竟如何生成圖像與影片的影片，由 Welch Labs 製作，Sanderson 則在數個月間提供編輯意見。他介紹 Welch 時說，這是「3blue1brown 在 YouTube 上真正的同道」。這是一組顯而易見的搭配，只是正式化了——兩個頻道都用動畫解釋數學，直到想法能被看見，而不是只能被相信。
3blue1brown.substack.com · x.com
楊立昆
曾經對談AMI Labs 執行董事長暨共同創辦人・紐約大學教授
Welch 那套兩集影片，講 LeCun 押注十億美元反對語言模型，是在 LeCun 本人協助下完成的，也帶著他的聲音：第二集一開場，Welch 問他，以 JEPA 為基礎的方法會不會超越如今驅動機器人的視覺—語言—動作模型（VLA），LeCun 回答：「喔，絕對會……VLA 注定失敗。」Welch 在結尾說，希望幾年後能再訪問他，看看 JEPA 走到了哪裡——這讓這套影片既是一份解釋，也是一場標了日期的賭注。
youtube.com · youtube.com
Chris Olah
思想同道Co-founder & Interpretability Lead, Anthropic
這是一組解讀上的搭配：Olah 畢生的工作，是讓神經網路的內部變得看得見；而 Welch 的頻道一再回到 Olah 的研究所促成的那些畫面。他談 AlexNet 的影片以一張激活圖譜（activation atlas）開場；他談可解釋性的影片，標題取自 Olah 自己的比喻——那些還沒人能抽取出來的特徵，是可解釋性的暗物質，而稀疏自編碼器就是望遠鏡。一個打造儀器，另一個讓一般觀眾看見儀器裡的東西。
youtube.com · youtube.com · distill.pub
