Beyond Machine Learning: Autonomous Learning

Frédéric Alexandre (1)

1 Mnemosyne - Mnemonic Synergy

Recently, Machine Learning has achieved impressive results, surpassing human performances, but these powerful algorithms are still unable to define their goals by themselves or to adapt when the task changes. In short, they are not autonomous. In this paper, we explain why autonomy is an important criterion for really powerful learning algorithms. We propose a number of characteristics that make humans more autonomous than machines when they learn. Humans have a system of memories where one memory can compensate or train another memory if needed. They are able to detect uncertainties and adapt accordingly. They are able to define their goals by themselves, from internal and external cues and are capable of self-evaluation to adapt their learning behavior. We also suggest that introducing these characteristics in the domain of Machine Learning is a critical challenge for future intelligent systems.

Mots clés: Machine Learning; Computational Neuroscience; Autonomous Learning

Domaines: Réseau de neurones [cs.NE]

Frédéric Alexandre. Beyond Machine Learning: Autonomous Learning. 8th International Conference on Neural Computation Theory and Applications (NCTA), Nov 2016, Porto, Portugal. pp.97 - 101, ⟨10.5220/0006090300970101⟩. ⟨hal-01401895⟩