Neil Zhu,簡書ID Not_GOD,University AI 創(chuàng)始人 & Chief Scientist,致力于推進世界人工智能化進程。制定并實施 UAI 中長期增長戰(zhàn)略和目標,帶領團隊快速成長為人工智能領域最專業(yè)的力量。
作為行業(yè)領導者,他和UAI一起在2014年創(chuàng)建了TASA(中國最早的人工智能社團), DL Center(深度學習知識中心全球價值網(wǎng)絡),AI growth(行業(yè)智庫培訓)等,為中國的人工智能人才建設輸送了大量的血液和養(yǎng)分。此外,他還參與或者舉辦過各類國際性的人工智能峰會和活動,產生了巨大的影響力,書寫了60萬字的人工智能精品技術內容,生產翻譯了全球第一本深度學習入門書《神經(jīng)網(wǎng)絡與深度學習》,生產的內容被大量的專業(yè)垂直公眾號和媒體轉載與連載。曾經(jīng)受邀為國內頂尖大學制定人工智能學習規(guī)劃和教授人工智能前沿課程,均受學生和老師好評。
問:什么樣的算法可以稱為是可非局部泛化的?
答:我指的非局部泛化算法是對那些與訓練過程中的輸入相距很遠的輸入也泛化得較好的學習算法。這類算法必須能夠對解釋數(shù)據(jù)的內在概念的新的組合進行泛化。近鄰方法和相關的像 kernal SVM 和 Decision Tree 算法只能在某些訓練樣本的空間鄰居上按照簡單的方式組合(like linear interpolation or linear extrapolation)進行比較好的泛化。因為解釋數(shù)據(jù)的內部概念的可能配置的數(shù)目是指數(shù)級大的,這些算法的泛化雖然不錯,但是還不足夠好。非局部泛化表示能夠泛化到超級大內在概念的可能的配置的空間的能力,那些新的數(shù)據(jù)可能會離觀測到的訓練數(shù)據(jù)很遠,遠遠超過訓練樣本的鄰居的訓練樣本的線性組合。
原文:
I mean that the algorithm should be able to provide good generalizations even for inputs that are far from those it has seen during training. It should be able to generalize to new combinations of the underlying concepts that explain the data. Nearest-neighbor methods and related ones like kernel SVMs and decision trees can only generalize in some neighborhood around the training examples, in a way that is simple (like linear interpolation or linear extrapolation). Because the number of possible configurations of the underlying concepts that explain the data is exponentially large, this kind of generalization is good but not sufficient at all. Non-local generalization refers to the ability to generalize to a huge space of possible configurations of the underlying causes of the data, potentially very far from the observed data, going beyond linear combinations of training examples that have been seen in the neighborhood of the given input.