【導(dǎo)讀】通常“學(xué)習(xí)”這個(gè)詞在現(xiàn)代社會(huì)有很多種解釋?zhuān)貏e是從計(jì)算機(jī)語(yǔ)言來(lái)看。在下面的部分，我們首先要從電腦視角去了解學(xué)習(xí)的意義，學(xué)習(xí)的主要特點(diǎn)之一。定推斷歸納總結(jié)的能力是學(xué)習(xí)中最重要的能力。知意識(shí)的真正的學(xué)習(xí)方法。反對(duì)學(xué)習(xí)就是算法的證據(jù)是人類(lèi)的學(xué)習(xí)能力來(lái)自于一些簡(jiǎn)單的例子。我要澄清一下,“學(xué)習(xí)”在這里不是指取得一個(gè)大學(xué)學(xué)。所以,人類(lèi)似乎是一個(gè)很慢的學(xué)習(xí)者。如果這樣的學(xué)習(xí)發(fā)生,完全未知的東西可能會(huì)得到正確的解釋,這個(gè)人必須去學(xué)習(xí)單詞之間的關(guān)系,以掌握這門(mén)語(yǔ)言。至少有50個(gè)學(xué)習(xí)方面的理論的已經(jīng)被認(rèn)知科學(xué)家寫(xiě)出來(lái)了。往會(huì)區(qū)分兩種形式的學(xué)習(xí):試驗(yàn)式的學(xué)習(xí)和證明式的學(xué)習(xí)。用了,但是我們不應(yīng)該像那樣去處理,因?yàn)樗馕吨鴮W(xué)習(xí)者已經(jīng)學(xué)會(huì)了邏輯法則。對(duì)于幫助人類(lèi)學(xué)習(xí)來(lái)說(shuō)就像一個(gè)教師。-在交互系統(tǒng)中,元知識(shí)被人類(lèi)老師人為地插入到計(jì)算機(jī)學(xué)習(xí)者大腦中。

　　

【正文】 inference [27], etc. I would exclude from the beginning any deterministic crisp approaches, either because things are genuinely random in nature (or at least have a significant random ponent), or because our models and our knowledge is far too gross and imperfect for creating crisp rules and dogmatic decisions. 5 Markov Random Fields Some recent work [17] showed evidence that the work of nouns (better described in psychophysical terms as work of “ideas”) is topologically a random work, while the work of relations, made up from pairs of ideas, is topologically scalefree. For example, pairs like “forkknife”, “doorwindow” e up much more frequently in trains of thought than “door” alone, or “window” alone. This indicates that the connections in these works are of varied strength, and actually are not always symmetric. For example, the idea “door” may trigger the idea “window” more frequently than the idea “window” triggers the idea “door”. This asymmetry in the interactions is a manifestation that Markov Random Fields (MRFs) are not applicable here in their usual form in which they are applied in image processing. An example of the interactions in a neighbourhood of an MRF, defined on a grid, is shown in Fig. 2b. This MRF, and the weights it gives for neighbouring interactions, cannot be expressed by a Gibbs joint probability density function. For example, the cell at the centre is influenced by its top left neighbour with weight ?1, but itself, being the bottom right neighbor of the cell at the top left, influences it with weight +1. This asymmetry leads to instability when one tries to relax such a random field, because local patterns created are not globally consistent (and therefore not expressible by global Gibbs distributions) [18]. According to Li [9,10,11], relaxations of such MRFs do not converge, but oscillate between several possible states. (Optimisations of Gibbs distributions either converge to the right interpretation, but more often than not, they hallucinate, . they settle on wrong interpretations.) So, one could model the work at each level of the tower of knowledge shown in Fig. 1, using a nonGibbsian MRF [5]. The interdependences between layers might also be modelled by such works, but perhaps it is more appropriate to use Bayesian models, as the interlayer dependencies are causal or diagnostic, rather than peertopeer. The question that arises then is: “where are we going to get the knowledge to construct these works?” Where does the mother that teaches her child get it from? There is no “ground truth” or universal knowledge the mother transfers to her child: she sees something and talks about it to the child, then she remembers something else, according to her own work of related ideas that invoke each other and are prompted by her own sensory input, talks again to the child, and so on. So, all the mother (the teacher) does is to transfer to the child her own connections between ideas and concepts. If the mother tells the child “This is a pencil and that is a rubber. The pencil helps us write and the rubber helps us erase what we wrote.”, the child will make the same connections as the mother had in her own brain. Pencilrubber will have a strong mutual recall in the child?s work of nouns, as well as writeerase in the child?s work of verbs. So, one thing we can do is to model our own mental connections between ideas and functionalities. Then let the child (the puter) ask the right questions. For every answer, the strength of the corresponding connection is increased. We may turn these strengths into probabilities. Then a totally new scene may be shown to the puter. The child/puter must be able to use the connections it has learnt to interpret this new scene. In practice, this is done by using manually annotated images. Heesch and Petrou [5] did exactly this to interpret outdoor scenes of buildings: they used hundreds of annotated images to learn the Markov dependencies of region configurations, defining the neighbourhood of a region to be the six regions that fulfil one of the following geometric constraints: it is above, below, to the left, to the right, it is contained by, or contains the region under consideration. An unknown scene was then labelled using a preliminary labelling performed on the basis of individual measurements made on each region, and relaxing the MRF defined on the segmented regions, using graph colourings and drawing labels for each region according to the local conditional probability of labels, conditioned on the current labels of the neighbours. No global consistency is guaranteed that way, but no global consistency exists, when the interdependencies between labels are asymmetric. We may intuitively understand this, as in an outdoor environment the long range interactions between objects are probably too weak to have a significant effect on the identity of a region. For example, if this region that belongs to this house here is a door, that region that is at the other end of the Fig. 1. The tower of knowledge: how knowledge may be anised. The doubleheaded arrows represent contextual interactions. The thin continuous arrows represent queries. The dashed arrows represent answers, . transfer of information. The level of interest in a cognitive vision task is the level of nouns, where we wish to assign labels to objects. Examples of nodes with contextual connotations in the work of nouns are “door”, “window”, “balcony”. Examples of nodes with contextual connotations in the work of functionality are “l(fā)ets air in”, “l(fā)ets light in”, “allows a person to enter”. Examples of nodes with contextual connotations in the work of descriptions are “has a glass pane”, “is at eyelevel”, “has a handle to open it”.field of view may be a car, a bush, a window, a house, or a tree. The differentiation of s