Experimental data is often not only highly dimensional, but also noisy and full of artefacts. This makes it difficult to interpret the data. Now a team has designed software that uses self-learning neural networks to compress the data in a smart way and reconstruct a low-noise version in the next step. This enables it to recognize correlations that would otherwise not be discernible. The software has now been successfully used in photon diagnostics at the FLASH free electron laser at DESY. But it is suitable for very different applications in science.