# CIFAR-10 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/cifar-10
> Markdown URL: https://aitinkerers.org/technologies/cifar-10.md
> Technology record last updated: 2026-02-23T23:07:03Z
> Generated: 2026-09-20T12:30:44Z

A foundational computer vision dataset featuring 60,000 labeled 32x32 color images across 10 distinct object classes.

Curated by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton, CIFAR-10 is a staple benchmark for training convolutional neural networks (CNNs). The collection includes 6,000 images per category: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck. Researchers utilize the 50,000 training and 10,000 test samples to prototype architectures quickly due to the manageable 32x32 resolution. It remains a primary tool for evaluating image classification performance and algorithmic efficiency in deep learning.

- Official technology site: https://www.cs.toronto.edu/~kriz/cifar.html
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [TinyEye: Image Classification on a $4 Microcontroller — Zero Floating-Point, Zero GPU](https://tokyo.aitinkerers.org/talks/rsvp_h4mfTwScVjU)

Live demo of CIFAR-10 image classification running entirely on a Raspberry Pi Pico ($4, 256KB RAM, ARM Cortex-M0+) using integer-only arithmetic. No floating-point unit. No GPU. No cloud. The core innovation is CIA (Constructive Integer Attention) — a new mathematical framework that replaces floating-point matrix operations in neural networks with pure integer computation derived from Egyptian fraction decomposition theory. In the demo, we also briefly show CIFAR-10 sample images to the Pico and show real-time classification results on screen. If possible, I also briefly show TinyLLM — a language model generating grammatical English sentences on the same $4 chip — to demonstrate this is a general-purpose inference architecture, not a single-task trick. Technical walkthrough covers: - The CIA architecture that eliminates floating-point entirely (not quantization — the model is natively integer) - Memory layout tricks to fit a working neural network in 256KB **This demo will be presented by two people: Yuichi Suzuki (CEO, BothSides Technology) and Yoshifumi Nagano (team member). Yuichi is recovering from upper arm surgery and being discharged from the hospital on February 19th. He can present and explain the technical details but needs a second person to physically handle the demo hardware. We would appreciate two presenter spots.

- Event context: AI Tinkerers Tokyo - Toranomon Meetup - February 19, 2026 — 2026-02-19 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_h4mfTwScVjU

## Related Technologies

- [256KB RAM](https://aitinkerers.org/technologies/256kb-ram) ([Markdown](https://aitinkerers.org/technologies/256kb-ram.md)) — 1 public demo
- [ARM Cortex-M0+](https://aitinkerers.org/technologies/arm-cortex-m0) ([Markdown](https://aitinkerers.org/technologies/arm-cortex-m0.md)) — 1 public demo
- [C](https://aitinkerers.org/technologies/c-2) ([Markdown](https://aitinkerers.org/technologies/c-2.md)) — 6 public demos
- [CIA (Constructive Integer Attention)](https://aitinkerers.org/technologies/cia-constructive-integer-attention) ([Markdown](https://aitinkerers.org/technologies/cia-constructive-integer-attention.md)) — 1 public demo
- [Integer-only arithmetic](https://aitinkerers.org/technologies/integer-only-arithmetic) ([Markdown](https://aitinkerers.org/technologies/integer-only-arithmetic.md)) — 1 public demo
- [no floating-point libraries](https://aitinkerers.org/technologies/no-floating-point-libraries) ([Markdown](https://aitinkerers.org/technologies/no-floating-point-libraries.md)) — 1 public demo
- [Raspberry Pi Pico](https://aitinkerers.org/technologies/raspberry-pi-pico) ([Markdown](https://aitinkerers.org/technologies/raspberry-pi-pico.md)) — 2 public demos
- [TinyLLM](https://aitinkerers.org/technologies/tinyllm) ([Markdown](https://aitinkerers.org/technologies/tinyllm.md)) — 1 public demo