# FER2013 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/fer2013
> Markdown URL: https://aitinkerers.org/technologies/fer2013.md
> Technology record last updated: 2026-02-22T15:37:03Z
> Generated: 2026-09-20T23:56:34Z

FER2013 is a benchmark dataset of 35,887 grayscale facial images used to train and evaluate emotion recognition models across seven distinct categories.

Pierre-Luc Carrier and Aaron Courville designed this dataset for the ICML 2013 Challenges in Representation Learning. It contains 48x48 pixel images labeled with seven emotions: anger, disgust, fear, happiness, sadness, surprise, and neutral. While the dataset is known for its high noise levels and label ambiguity, it remains a critical baseline for testing convolutional neural networks (CNNs) in real-time facial expression analysis.

- Official technology site: https://www.kaggle.com/datasets/msambare/fer2013
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Modèle CNN comme Deep Learning pour la reconnaissance des expressions faciales](https://conakry.aitinkerers.org/talks/rsvp_SsgPDZp0VSw)

Optimisation d’un modèle CNN pour la reconnaissance des expressions faciales (FER2013) » La présentation portera sur : L’architecture CNN utilisée (ResNet18 et ResNet50 en transfer learning), Les choix méthodologiques (split stratifié, gestion du déséquilibre), Les techniques de régularisation (mixup, label smoothing, dropout), Les décisions d’optimisation et les difficultés rencontrées, Une analyse des performances obtenues (Accuracy et F1 macro).

- Event context: AI Demo Day @ Kofi Annan - 25/02/26 — 2026-02-25 — Conakry
- Public talk page: https://conakry.aitinkerers.org/talks/rsvp_SsgPDZp0VSw

## Related Technologies

- [Dropout](https://aitinkerers.org/technologies/dropout) ([Markdown](https://aitinkerers.org/technologies/dropout.md)) — 1 public demo
- [Mixup](https://aitinkerers.org/technologies/mixup) ([Markdown](https://aitinkerers.org/technologies/mixup.md)) — 1 public demo
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [ResNet-18](https://aitinkerers.org/technologies/resnet-18) ([Markdown](https://aitinkerers.org/technologies/resnet-18.md)) — 1 public demo
- [ResNet-50](https://aitinkerers.org/technologies/resnet-50) ([Markdown](https://aitinkerers.org/technologies/resnet-50.md)) — 1 public demo
- [Transfer learning](https://aitinkerers.org/technologies/transfer-learning) ([Markdown](https://aitinkerers.org/technologies/transfer-learning.md)) — 4 public demos