«   2018年8月   »
12345
6789101112
13141516171819
20212223242526
2728293031
控制面板
您好,欢迎到访网站!
  查看权限
网站分类
搜索
最新留言
    文章归档
    友情链接
      当前位置:网站首页 / www.bogou800.com / 正文内容

      一张图看懂野生智能各年夜 门派

      2017年04月12日 | 分类: | 406 浏览 | 0 评论

      文/唐杉 

      来源:矽说

      咱们当初道的人工智能,良多时辰指的是基于深度神经收集的机械学习(或许深度学习)圆法。当心现实上,人工智能是一个近况长久和丰盛内在的学科。因为这两年机械学习获得了十分好的实践效果,别的研讨标的目的仿佛被人人忘记了。比来这类情形有点变更,好像其它偏向也在更多的收回声响。比方,前两天看到的一个消息,“米国国防部高等打算研究局(DARPA)于未几前对付Gamalon注资720万美圆”。这个Gamalon就是玩“Bayesian programming”的,uc彩票网

      恰好今天看到两篇挺有意思的文章,都是聊人工智能范畴的各个“部落”(本文是tribes)。我感到用“门派”也挺适合。虽然同在人工智能这个“武林”,他们的闭系也很奥妙,既有合作,也有配合,偶然还会“badmouth each other”。一篇是“AI’s Factions Get Feisty. But Really, They’re All on the Same Team”[1],第发布篇是“The Many Tribes of Artificial Intelligence”[2]。特殊是第二篇,还用来一张信息图抽象的描写了他们之间的关联。

      图片来自Intuition Machine, medium.com

      这篇作品的作家无比“严正”的给每一个“部落”起了名字(固然也有的是公认的),还设想了“徽章”。我第一眼就看到了PAC Theorists谁人。

      上面我便搬运一下各个“部降”的阐明。下明的局部是Deep Learning,多少个分收名字起的有面意义,式样也有亮点!

      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.

      (简要翻译:符号主义者-用逻辑符号系统进行推理。重要问题是,人们总能找到一些逻辑规矩的破例情况。看起来事实世界的逻辑并非爱憎分明的,而存在必定水平的灰色天带,因此应方法碰到了瓶颈。)

      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).

      (简要翻译:进化算法主义者-用基因进化算法禁止野生智能运算,引进随机渐变,保存最佳的部分,并镌汰后果较好的部门。在深度教习算法中,也可使用基果退化算法去部分代替梯度降落算法往做劣化,因而进化算法和深度学习并不是冰炭不洽。)

      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.

      (简要翻译:Bayes流- 依附几率来做推理,使用诸如概率图模型[Probabilistic Graph Models]和受特卡洛算法之类的对象。取标记主义者相相似的是,Bayes流做人工智能办法也能够在逻辑上获得说明,并且借能度化不断定性。今朝有联合Bayes方式和深度学习算法的库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.

      (简要翻译:Kernel守旧主义者-深度学习之前,SVM是最水的算法,其时使用Kernel Trick能够把非线性的问题映射到线性立体。Kernel保守主义者对Kernel方法的文雅性大加赞成,而且认为搞深度学习的不过就是一帮自己也不懂本人搞出来的是甚么货色的炼金方士。)

      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.

      (扼要翻译:抱树者- 那帮人应用基于树的模型,比方随机丛林,决议树等等现实上基于树的模型正在Kaggle中的很多题目里很有效。微硬有一个本相,融会了树范型跟深量进修。)

      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.

      (简要翻译:联结主义者- 一群信任智能行动来源于年夜范围神经元互联的人。第一波是1959年的Perceptron,以后经由起升沉伏,比来一次振兴就是今朝风心浪尖的深度学习。连贯主义内部也不是铁板一起,而是分为几个宗派:)

      The Canadian Conspirators - Hinton, LeCun, Bengio et al. End-to-end deep learning without manual feature engineering.

      (减拿年夜派- Hinton,LeCun,Bengio等等,特技是没有须要脚工做feature engineering的端到端进修)

      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.

      (瑞士帮- LSTM的提出者以及宣称使用两个互相合营的RNN就可以解决意识问题的帮派。任何敢声称自己在他们之前就创造了什么东西的人都邑被瑞士帮喷到逝世。比如,瑞士帮最近就号称实际上是他们发现了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.

      (英国狗娃- 搞出了AlphaGo的帮派,认准了AI就是深度学习加加强学习[ 固然LeCun说删强学习不外是蛋糕上的樱桃装点]。DeepMind是英国狗娃外面做得最杰出的团队)

      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”.

      (猜测主义学者- 搞无监督学习的人,依据LeCun无监督学习是AI蛋糕中最大的部分,相称于宇宙中的暗物资,也是目前还没有解决的发域)

      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.

      (简要翻译:紧缩主义者-认为认知和学习的本度是信息压缩,和信息论的思维头绪分歧。)

      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.

      (简要翻译:庞杂系统理论家- 使用从物理学,能量模型,复纯体系实践,浑沌理论和统计力学等学科继续来的方法。他们最自得的做品就是Swarm AI。别的他们是最有盼望可能给深度学习给出理论解释的人。)

      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.

      (简要翻译:仿死主义者-爱好搞仿生学的东东,做模拟真挚生物神经元的模型,例如Numenta的那帮人,和在IBM弄TrueNorth的团队。)

      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.

      (简要翻译:功效联结图谱论者- 认为大脑里的相互联结,即功能联结图谱,是智能的真正来源。这方里的名目包含天然蠕虫和取得大批赞助的脑功能映射项目。)

      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.

      (简要翻译:疑息散成工程师- 认为机器认识起源于机器外部对实在天下中因果性的映照。这个集团以为我们必需起首意识“意识”的实质,才干做人工智能)

      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.

      (简要翻译:PAC主义者- 这群人其实不念实正探讨人工智能。他们的观念是,只有一个自顺应系统能疾速履行大概率远似准确的盘算[probably approximately correct, PCA]就止。总而行之,智能基本不应基于大规模计算)

      再说一点题中话,深度神经网络几个比拟大的问题,好比“乌盒”问题,无监视学习,能耗的问题(和人类比拟),有可能将来皆要靠学习其余“门派”的“武功”来处理。

      T.S.

      参考:

      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

      上一篇:谭咏麟《念唱》逢困难济急 粉丝年夜多没有会唱粤语 下一篇:篮网总结 书豪果伤病易展四肢 潜伏状元签黑收人

      额 本文暂时没人评论 来添加一个吧

      发表评论

      必填

      选填

      选填

      ◎欢迎参与讨论,请在这里发表您的看法、交流您的观点。