"AI by Arms": Prof. Tom Yeh teaches autoencoders with a standing classroom exercise
ProfTomYeh · x · 2026-09-09
Prof. Tom Yeh shares his classroom method for teaching autoencoders with a physical exercise, plus a full worked example.
- The metaphor: hold a 900-page textbook with arms wide, squeeze hands down to palm size at your neck—that's the encoder and bottleneck; pushing arms back out and rebuilding the book from palm notes is the decoder, with the gap being the loss
- Worked demo compressing 4 numbers to 2: inputs copied as targets (why "auto"), two encoder layers with weights/biases/ReLU, a 2-dim bottleneck, symmetric decoder, then MSE gradients 2×(Y−Y′) driving backprop
- Punchline: your entire education is encoding and decoding
More from Research
- Ben Lorica: Your Model Is a Rental, the Improvement Loop Is the Asset—Forget RSI Hype — bigdata · 2026-09-09
- In 2000, Alain Connes Said the Millennium Problems Were 'Totally Inaccessible to Computers' — minilek · 2026-09-09
- Researcher calls for mathematically defined problem lists in every field, citing AI's scalable verification — ValerioCapraro · 2026-09-09
- Dev Spotlight: Transformers Forced to Predict Themselves and Build Belief States — yacinelearning · 2026-09-09
- Open-source 4B VLM RL-trained to play GeoGuessr beats GPT 5.4 mini and Haiku on one A100 — SergioPaniego · 2026-09-09
- Granularity and the 'birdiest bird': self-supervised clusters cut across ImageNet labels — y_m_asano · 2026-09-09