Its deep learning capability is further enhanced by using inhibition, correlation and by its ability to cope with incomplete data, or "lost" neurons or layers even amidst a task.
The link-weights allow dynamic determination of innovation and redundancy, and facilitate the ranking of layers, of filters or of individual neurons relative to a task.
LAMSTAR has been applied to many domains, including medical[4][5][6] and financial predictions,[7] adaptive filtering of noisy speech in unknown noise,[8] still-image recognition,[9] video image recognition,[10] software security[11] and adaptive control of non-linear systems.
[12] LAMSTAR had a much faster learning speed and somewhat lower error rate than a CNN based on ReLU-function filters and max pooling, in 20 comparative studies.
[13] These applications demonstrate delving into aspects of the data that are hidden from shallow learning networks and the human senses, such as in the cases of predicting onset of sleep apnea events,[5] of an electrocardiogram of a fetus as recorded from skin-surface electrodes placed on the mother's abdomen early in pregnancy,[6] of financial prediction[1] or in blind filtering of noisy speech.