Deep Learning – the new kid in Artificial Intelligence · News · Biometrics Institute

Billions of neurons in our brain are wired together in a sophisticated manner to give us the amazing ability of learning all sort of things. Artificial Neural Networks (ANNs) were proposed more than six decades ago (precisely in 1943) in an attempt to develop intelligent algorithms that can mimic the fascinating capabilities of the visual cortex part of human brain in making sense of the external world around us. Up until the last few years, all ANN based solutions were too simple, in terms of their structures and the total number of neurons, to tackle complex real-life problems such as biometric recognition. In fact, building complex and'deep' ANN was not easily feasible for two key reasons: the lack of computation powers and the limited availability of training data. The introduction of powerful and affordable GPUs for training ANN in recent years along with the availability of large volume of labelled data has led to the emergence of Deep Learning as a state-of-art machine learning approach.