Using deep learning techniques mutated by evolutionary algorithms, the temporal prediction class of intelligence at Qopius is fundamentally laid out over the Q-Engine structure.

In the data acquisition layer, the model acquires application-relevant information from all available data streams. This time series data collected can have many different forms: text, audio, imagery and equivalently can be acquired from all possible sources: web harvesting, social media, news, publications and journals, existing databases.

In the representation layer, the model maps out the correlations and structures it can extract from the data.

In the prediction layer, based on the expert knowledge in the particular field of application, it generates and combines numerous predictions in order to result in the desired prediction of the outcome. Predictions are verified and the performance of the predictive model is adjusted accordingly by refining its attentional control over the data acquisition layer and assigning high confidence on the most successful paths taken.

Learn more about the Qopius Engine and how it works