Four XOR observations
Reference inputs · synthetic data
- Records
- 4
- Data columns
- 3
- Missing cells
- 0
- Duplicate records
- 0
- Feature duplicates
- 0
4 of 4 records · One record = one observation. Statistics and downloads use all records.
About this dataset
All four pairs of −1 and +1. Opposite signs have class 1; matching signs have class 0. This complete truth table isolates the effect of the hidden activation.
- Both classes have two observations. The diagonal arrangement matters more than individual feature averages.
- There is no holdout set: this experiment examines representation on these four fixed inputs.
- Weights, threshold, and activation are model settings and do not change this dataset.
Counts exclude the row identifier. Duplicate counts are extra occurrences after the first. Feature duplicates ignore labels and experimental conditions. — means a statistic is undefined or not applicable.
- Row
- Stable identifier within this synthetic fixture.
- Input x
- First signed input.
- Input y
- Second signed input.
- True class
- 0 for matching signs, 1 for opposite signs.