Training and evaluating a model
S5 (1re) to S6 (Terminale) · 🤖 Artificial intelligence · 🛠️ Technology and digital skills
Data preparation, gradient descent training, preventing overfitting, and model evaluation with accuracy, precision, recall and confusion matrix.
- Questions
- 24, in 4 parts: Data · Training · Evaluating · Best practices
- Chapter
- Training and evaluating a model
- Game
- Pixelia
- Pack language
- English
A taste of what is inside
- Data is split into three sets: training, validation and...backupholidayssportstest
- Settings chosen before training, like layer count, are...hyperparameterslabelspixelsweights
- A model's accuracy is...computation timelayer countmodel sizethe share of correct predictions
How to get it
In your game (full version): ⚙️ Settings → 📚 Question bank, choose this pack, then “Buy”. The payment opens in your browser; the pack then installs itself and stays available on every device of your licence.
Try Pixelia: the free demo