我們現在說的人工智慧，很多時候指的是基於深度神經網路的機器學習（或者深度學習）方法。但實際上，人工智慧是一個歷史悠久和豐富內涵的學科。由於這兩年機器學習取得了非常好的實際效果，其它研究方向似乎被大家遺忘了。最近這種情況有點變化，似乎其它方向也在更多的發出聲音。比如，前兩天看到的一個新聞，“美國國防部高階計劃研究局（DARPA）於不久前對Gamalon注資720萬美元”。這個Gamalon就是玩“Bayesian programming”的。
正好昨天看到兩篇挺有意思的文章，都是聊人工智慧領域的各個“部落”（原文是tribes）。我覺得用“門派”也挺合適。雖然同在人工智慧這個“武林”，他們的關係也很微妙，既有競爭，也有合作，有時還會“badmouth each other”。一篇是“AI’s Factions Get Feisty. But Really, They’re All on the Same Team”[1]，第二篇是“The Many Tribes of Artificial Intelligence”[2]。特別是第二篇，還用來一張資訊圖形象的描述了他們之間的關係。
圖片來自Intuition Machine, medium.com
這篇文章的作者非常“嚴肅”的給每個“部落”起了名字（當然也有的是公認的），還設計了“徽章”。我第一眼就看到了PAC Theorists那個。
下面我就搬運一下各個“部落”的說明。高亮的部分是Deep Learning，幾個分支名字起的有點意思，內容也有亮點！
Symbolists - Folks who used symbolic rule-based systems to make inferences. Most of AI has revolved around this approach. The approaches that used Lisp and Prolog are in this group, as well as the SemanticWeb, RDF, and OWL. One of the most ambitious attempts at this is Doug Lenat’s Cyc that he started back in the 80’s, where he has attempted to encode in logic rules all that we understand about this world. The major flaw is the brittleness of this approach, one always seems to find edge cases where one’s rigid knowledge base doesn’t seem to apply. Reality just seems to have this kind of fuzziness and uncertainty that is inescapable. It is like playing an endless game of Whack-a-mole.
（簡要翻譯：符號主義者-用邏輯符號系統進行推理。主要問題是，人們總能找到一些邏輯規則的例外情況。看起來現實世界的邏輯並不是涇渭分明的，而存在一定程度的灰色地帶，因此該方法遇到了瓶頸。）
Evolutionists - Folks who apply evolutionary processes like crossover and mutation to arrive at emergent intelligent behavior. This approach is typically known as Genetic Algorithms. We do see GA techniques used in replacement of a gradient descent approach in Deep Learning, so it’s not a approach that lives in isolation. Folks in this tribe also study cellular automata such as Conway’s Game of Life [CON] and Complex Adaptive Systems (CAS).
（簡要翻譯：進化演算法主義者-用基因進化演算法進行人工智慧運算，引入隨機突變，保留最好的部分，並淘汰效果較差的部分。在深度學習演算法中，也可以使用基因進化演算法來部分取代梯度下降演算法去做優化，因此進化演算法和深度學習並非水火不容。）
Bayesians - Folks who use probabilistic rules and their dependencies to make inferences. Probabilistic Graph Models (PGMs) are a generalization of this approach and the primary computational mechanism is the Monte-Carlo method for sampling distributions. The approach has some similarity with the Symbolist approach in that there is a way to arrive at an explanation of the results. One other advantage of this approach is that there is a measure of uncertainty that can be expressed in the results. Edward is one library that mixes this approach with Deep Learning.
（簡要翻譯：Bayes流- 依靠概率去做推理，使用諸如概率圖模型[Probabilistic Graph Models]和蒙特卡洛演算法之類的工具。與符號主義者相類似的是，Bayes流做人工智慧方法也可以在邏輯上得到解釋，而且還能量化不確定性。目前有結合Bayes方法和深度學習演算法的庫Edward。）
Kernel Conservatives - One of the most successful methods prior to the dominance of Deep Learning was SVM. Yann LeCun calls this glorified template matching. There is what is called a kernel trick that makes an otherwise non-linear separation problem into one that is linear. Practitioners in this field live in delight over the mathematical elegance of their approach. They believe the Deep Learners are nothing but alchemists conjuring up spells without the vaguest of understanding of the consequences.
（簡要翻譯：Kernel保守主義者-深度學習之前，SVM是最火的演算法，當時使用Kernel Trick可以把非線性的問題對映到線性平面。Kernel保守主義者對於Kernel方法的優雅性大加讚許，並且認為搞深度學習的無非就是一幫自己也不懂自己搞出來的是什麼東西的煉金術士。）
Tree Huggers - Folks who use tree-based models such as Random Forests and Gradient Boosted Decision Trees. These are essentially a tree of logic rules that slice up the domain recursively to build a classifier. This approach has actually been pretty effective in many Kaggle competitions. Microsoft has an approach that melds the tree based models with Deep Learning.
（簡要翻譯：抱樹者- 這幫人使用基於樹的模型，例如隨機森林，決策樹等等事實上基於樹的模型在Kaggle中的許多問題裡很有用。微軟有一個模型，融合了樹模型和深度學習。）
Connectionists - Folks who believe that intelligent behavior arises from simple mechanisms that are highly interconnected. The first manifestation of this were Perceptrons back in 1959. This approach died and resurrected a few times since then. The latest incarnation is Deep Learning.
（簡要翻譯：聯結主義者- 一群相信智慧行為來源於大規模神經元互聯的人。第一波是1959年的Perceptron，之後經過起起伏伏，最近一次復興就是目前風口浪尖的深度學習。聯結主義內部也不是鐵板一塊，而是分為幾個宗派：）
The Canadian Conspirators - Hinton, LeCun, Bengio et al. End-to-end deep learning without manual feature engineering.
（加拿大派- Hinton，LeCun，Bengio等等，絕技是不需要手工做feature engineering的端到端學習）
Swiss Posse - Basically LSTM and that consciousness has been solved by two cooperating RNNs. This posse will have you lynched if you ever claim that you invented something before they did. GANs, the “coolest thing in the last 20 years” according to LeCun are also claimed to be invented by the posse.
（瑞士幫- LSTM的提出者以及宣稱使用兩個互相配合的RNN就能解決意識問題的幫派。任何敢宣稱自己在他們之前就發明了什麼東西的人都會被瑞士幫噴到死。比如，瑞士幫最近就號稱其實是他們發明了GAN）
British AlphaGoist - Conjecture that AI = Deep Learning + Reinforcement Learning, despite LeCun’s claim that it is just the cherry on the cake. DeepMind is one of the major proponents in this area.
（英國狗娃- 搞出了AlphaGo的幫派，認準了AI就是深度學習加增強學習[ 雖然LeCun說增強學習不過是蛋糕上的櫻桃點綴]。DeepMind是英國狗娃裡面做得最出色的團隊）
Predictive Learners - I’m using the term Yann LeCun conjured up to describe unsupervised learning. The cake of AI or the dark matter of AI. This is a major unsolved area of AI. I, however, tend to believe that the solution is in “Meta-Learning”.
（預測主義學者- 搞無監督學習的人，根據LeCun無監督學習是AI蛋糕中最大的部分，相當於宇宙中的暗物質，也是目前尚未解決的領域）
Compressionists - Cognition and learning are compression (Actually an idea that is shared by other tribes). The origins of Information theory derives from an argument about compression. This is a universal concept that it is more powerful than the all too often abused tool of aggregate statistics.
（簡要翻譯：壓縮主義者-認為認知和學習的本質是資訊壓縮，和資訊理論的思想脈絡一致。）
Complexity Theorists - Employ methods coming from physics, energy-based models, complexity theory, chaos theory and statistical mechanics. Swarm AI likely fits into this category. If there’s any group that has a chance at coming up with a good explanation why Deep Learning works, then it is likely this group.
（簡要翻譯：複雜系統理論家- 使用從物理學，能量模型，複雜系統理論，混沌理論和統計力學等學科繼承來的方法。他們最得意的作品就是Swarm AI。另外他們是最有希望能夠給深度學習給出理論解釋的人。）
Biological Inspirationalists - Folks who create models that are closer to what neurons appear in biology. Examples are the Numenta folks and the Spike-and-Integrate folks like IBM’s TrueNorth chip.
（簡要翻譯：仿生主義者-喜歡搞仿生學的東東，做模模擬正生物神經元的模型，例如Numenta的那幫人，以及在IBM搞TrueNorth的團隊。）
Connectomeist - Folks who believe that the interconnection of the brain (i.e. Connectome) is where intelligence comes from. There’s a project that is trying to replicate a virtual worm and there is some ambitious heavily funded research [HCP] that is trying to map the brain in this way.
（簡要翻譯：功能聯結圖譜論者- 認為大腦裡的互相聯結，即功能聯結圖譜，是智慧的真正來源。這方面的專案包括人造蠕蟲和獲得大量資助的腦功能對映專案。）
Information Integration Theorists - Argue that consciou-ness emerges from some internal imagination of machines that mirrors the causality of reality. The motivation of this group is that if we are ever to understand consciousness then we have to at least start thinking about it! I, however, can’t see the relationship of learning and consciousness in their approach. It is possible that they aren’t related at all! That’s maybe why we need sleep.
（簡要翻譯：資訊整合工程師- 認為機器意識來源於機器內部對真實世界中因果性的對映。這個團體認為我們必須首先認識“意識”的本質，才能做人工智慧）
PAC Theorists - Are folks that don’t really want to discuss Artificial Intelligence, rather prefer just studying intelligence because at least they know it exists! Their whole idea is that adaptive systems perform computation expediently such that they are all probably approximately correct. In short, intelligence does not have the luxury of massive computation.
（簡要翻譯：PAC主義者- 這群人並不想真正討論人工智慧。他們的觀點是，只要一個自適應系統能快速執行大機率近似正確的計算[probably approximately correct, PCA]就行。總而言之，智慧根本不該基於大規模計算）
再說一點題外話，深度神經網路幾個比較大的問題，比如“黑盒”問題，無監督學習，能耗的問題（和人類相比），有可能未來都要靠學習別的“門派”的“武功”來解決。
T.S.
參考：
1. CADE METZ，“AI’s Factions Get Feisty. But Really, They’re All on the Same Team”，wired.com
2. Carlos E. Perez, “The Many Tribes of Artificial Intelligence”，Medium.com