On-the-Fly Learning in a Perpetual Learning Machine
(Submitted on 3 Sep 2015 (v1), last revised 8 Sep 2015 (this version, v2))
Despite the promise of brain-inspired machine learning, deep neural networks (DNN) have frustratingly failed to bridge the deceptively large gap between learning and memory. Here, we introduce a Perpetual Learning Machine; a new type of DNN that is capable of brain-like dynamic 'on the fly' learning because it exists in a self-supervised state of Perpetual Stochastic Gradient Descent. Thus, we provide the means to unify learning and memory within a machine learning framework.
盡管腦啟發的機器學習的承諾，深層神經網絡（DNN）都令人沮喪未能彌合學習和記憶之間的欺騙性很大的差距。在這里，我們介紹一個永久的學習機;一種新型DNN的是能夠腦般的動感'飛'的學習，因為它存在于永久隨機梯度下降的自我監管的狀態。因此，我們提供給機器學習框架內統一的學習和記憶的手段。（google翻譯）
Download:
