1 / 66

計算機概論

計算機概論. 100701035 應數一黃楚耘. 報告內容. 11.4 Additional Areas of Research 其他研究領域 11.5 Artificial Neural Networks 類神經網路. 11.4 Additional Areas of Research 其他研究領域. Representing and manipulating knowledge 知識的表示及處理 Learning 學習 Genetic algorithms 基因演算法. 前言.

dearnhardt
Download Presentation

計算機概論

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. 計算機概論 100701035 應數一黃楚耘

  2. 報告內容 • 11.4 Additional Areas of Research 其他研究領域 • 11.5 Artificial Neural Networks 類神經網路

  3. 11.4 Additional Areas of Research其他研究領域 • Representing and manipulating knowledge 知識的表示及處理 • Learning 學習 • Genetic algorithms 基因演算法

  4. 前言 • We explore issues of handling knowledge(處理知識), learning(學習), and dealing with complex problems, which continue to challenge researchers in the field of artificial intelligence. These activities involve capabilities that appear to be easy for human minds but apparently tax the capabilities of machines. • For now, much of the progress in developing “intelligent” agents has been achieved essentially by avoiding direct confrontation with these issues – perhaps by applying clever shortcuts or limiting the scope in which a problems arises.

  5. Representing and Manipulating knowledge知識的表示及處理 • Real–world knowledge(現實知識): understanding images requires a significant amount of knowledge about the items in the image and that the meaning of a sentence might depend on its context. • Giving machines this capability is a major challenge in artificial intelligence.

  6. This is complicated by the fact that knowledge occurs in both declarative(宣告式) and procedural(程序式) forms. • Procedural knowledge(程序式知識) involves a trial and error process by which an agent learns appropriate actions by being punished for poor actions and rewarded for good ones • Declarative knowledge(宣告式知識) takes the forms of expanding(擴充) oraltering(改變) the “fact” in an agent’s store of knowledge

  7. It is questionable to find a single scheme(方案) ultimately for representing all forms of knowledge. The knowledge must also be readily accessible(可被取用), and achieving this accessibility is a challenge. • Semantic nets(語意網絡):used as a means of knowledge representation and storage, but exacting information(萃取資料) from them can be problematic.

  8. Example1:”Mary hit John.” extracting such information during contextual analysis(文脈分析) could require a significant amount of searching(大量的搜索) through the net. • Example2 :”Did Arthur win the race?” “No” “No, he came down with the flu and was not able to compete.” Associative Memory(關聯式記憶)

  9. Related Information(相關資訊) • Relevant Information(切題資訊) • Example: ”No, he was born in January and his sister’s name is Lisa.”

  10. Meta-reasoning(後設推理) • Insert various forms of reasoning into the extraction process (reasoning about reasoning • 將各種推理形式插入萃取過程(有關推理本身的推理行為) • Closed-world Assumption(封閉式假說) • A statement is false unless it can be explicitly(明確地) derived from the information available. • Example:it is a closed-world assumption that allows a database to conclude that Nicole Smith does not subscribe to a particular magazine even though the database does not contain any information at all about Nicole.

  11. On the surface the close-world assumption appears trivial(瑣細;不重要的), but it has consequences that demonstrate how apparently innocent meta-reasoning techniques can have subtle, undesirable effects. 後果卻展現出一個表面上不起眼的後設推理技術如何產生重大而出乎意料的影響。 • Example: • ”Mickey is a mouse OR Donald is a duck.”

  12. Frame problem(框架問題) • Keeping stored knowledge up to date in a changing environment • If an intelligent agent is going to use its knowledge to determine its behavior, then that knowledge must be current. • But the amount of knowledge required to support intelligent behavior can be enormous, and maintaining that knowledge in a changing environment can be a massive undertaking.

  13. Learning(學習) • We would like to give intelligent agents the ability to acquire new knowledge. • We would like intelligent agents to be able to learn on their own.

  14. Level • Imitation(模仿) • Supervised training(監督式訓練) • Reinforcement(在強化)

  15. Imitation 模仿 • A person directly demonstrates(展示) the steps in a task (或許是透過一系列的電腦操作,或由實體移動機器人作完一系列的動作) and the computer simply records the steps. • Spreadsheets(試算表); word processors(文字處理器) ex:LaTex • Learning by imitation places little responsibility on the agent.

  16. 電子試算表,簡稱試算表(英文:spreadsheet),又稱電子數據表,是一類模擬紙上計算表格的計算機程序。它會顯示由一系列行與列構成的網格。單元格內可以存放數值、計算式、或文本。電子表格通常用於財務信息,因為它能夠頻繁的重新計算整個表格。電子試算表,簡稱試算表(英文:spreadsheet),又稱電子數據表,是一類模擬紙上計算表格的計算機程序。它會顯示由一系列行與列構成的網格。單元格內可以存放數值、計算式、或文本。電子表格通常用於財務信息,因為它能夠頻繁的重新計算整個表格。 • VisiCalc是第一個電子表格程序,用於蘋果II型電腦。 Lotus 1-2-3是用於IBM PC上DOS時代主要的電子表格程序。 而Numbers和Excel則分別是Mac OS X和Windows系統上主要的電子表格程序。 Calc則是可在多種平台上執行的Open Office與LibreOffice中的電子表格程序。

  17. Supervised training監督式訓練 A person identifies the correct response for a series of examples and then the agent generalizes from those examples to develop an algorithm that applies to new cases • 一個指出對一系列例子的正確回應,而代理人從這些例子做一般化而得到可用在新案例的演算法

  18. Training set(訓練集):the series of examples • Learning to recognize a person’s handwriting or voice, learning to distinguish between junk and welcome email, and learning how to identify a disease from a set of symptoms.

  19. Reinforcement再強化 • The agent is given a general rule(通用規則) to judge for itself when it has succeeded or failed at a task during trial and error. • Play chess西洋棋,checkers圍棋 • Success or Failure is easy to define • Allows the agent to act autonomously(自主地) as it learns to improve its behavior over time.

  20. Learning remains a challenging field of research since no general, universal principle has been found that covers all possible learning activities. • 既然還找不到一個能夠涵蓋所有可能學習活動的通用原則,學習仍然是一個極具挑戰性的領域。 • ALVINN (Autonomous Land Vehicles in a Neural Net) • 從一個人類駕駛收集資料,並且用那個資料來調整自己駕駛的決策。

  21. Discovery • Learning is “target based目標導向” whereas discovery is not - unexpected(意外) • Developing agents with the ability to discover efficiently requires that the agent be able to identify potentially fruitful “trains of thought(一系列想法)”, relies on the ability to reason and the use of heuristics(經驗法則). • Require that an agent be able to distinguish meaningful results from insignificant ones.

  22. Examples: ohm’s law of electricity Kepler’s third law of planetary motion conservation of momentum(動能守恆) AUTOCLASS:use infrared spectral data to discover new classes of stars that were previously unknown in astronomy

  23. Genetic Algorithms基因演算法 • A solution can sometimes be discovered through an evolutionary process(演進的過程) involving many generations of trial solutions. • In essence, genetic algorithms will discover a solution by random behavior combined with a simulation(模擬) of reproductive(生殖) theory and the evolutionary process of natural selection(天澤).

  24. A genetic algorithm begins by generating a random pool(庫) of trial solution (a random sequence of tile movements). • Each solution is just a guess. Each trial solution is called a chromosome(染色體) and each component of the chromosome is called a gene(基因). • Since each initial chromosome is a random guess, it is very unlikely that it will represent a solution to the problem at hand. Thus, the genetic algorithm proceeds to generate a new pool of chromosomes whereby each chromosome is an offspring (child) of two chromosomes (parents) of the previous pool.

  25. The parents are randomly selected from the pool giving a probabilistic preference to those chromosomes that appear to provide the best chance of leading to a solution, thereby emulating(盡力趕上) the evolutionary principle of survival of the fittest(適者生存). • Each offspring is a random combination of genes from the parents. • In addition, a resulting offspring may occasionally be mutated(變動) in some random way. Hopefully, by repeating this process over and over, better and better trial solutions will evolve(逐步形成) until a very good one, if not the best, is discovered.

  26. Unfortunately, there is no assurance that the genetic algorithm will ultimately find a solution, yet research has demonstrated that genetic algorithms can be effective in solving a surprisingly wide range of complex problems. • When applied to the task of program development, the genetic algorithm approach is known as evolutionary programming(演進式程式設計).

  27. Here the goal is to develop programs by allowing them to evolve rather than by explicitly writing them.(允許程式演化而不是直接地撰寫) • Researchers have applied(應用) evolutionary programming techniques to the program-development process(程式開發程序) using functional programming languages. • The approach has been to start with a collection of programs that contain a rich variety of functions.

  28. The functions in this starting collection form the “gene pool”(基因庫) from which future generations of programs will be constructed. • One then allows the evolutionary process to run for many generations, hoping that by producing each generation from the best performers in the previous generation, a solution to the target problem will evolve.

  29. 11.5 Artificial Neural Networks類神經網路 • Basic properties 基本性質 • Training artificial neural network 訓練類神經網路 • Associative memory 關聯記憶

  30. 前言 • Sequences of instructions(指令) do not seem capable of perceiving(感知) and reasoning(推理) at levels comparable to those of the human mind. • Artificial Neural Network 類神經網路

  31. Basic Properties基本性質 • Artificial Neural Networks 類神經網路 • provide a computer processing model that mimics networks of neurons in living biological systems • neurons神經單位(細胞); 神經元

  32. dendrites樹突 • axon 軸突 • these dendrites pick up signals from the axons of other cells across small gaps known as synapses(神經鍵;突觸 ).

  33. Whether the particular input signal will have an exciting(發動) or inhibiting(抑制) effect on the neuron is determined by the chemical composition of the synapse. • It is believed that a biological neural network learns by adjusting(調整) these chemical connections between neurons.

  34. a neuron in an artificial neural network is a software unit that mimics this basic understanding of a biological neuron • it produces an output of 1 or 0, depending on whether its effective input exceeds a given value, which is called the neuron’s threshold value(臨界值) • effective input(有效輸入值) • a weighted sum of the actual inputs

  35. Neuron Computeeffective input: Compare effective Input to threshold value Produce output Of 0 or 1

  36. weights權重 if this sum exceeds the neuron’s threshold value, the neuron produces an output of 1(模擬一個神經細胞的發動狀態); otherwise the neuron produce a 0 as its output(模擬抑制狀態)

  37. -2 1.5 3 -1

  38. A weight can be positive or negative means that the corresponding input can have either an inhibiting or exciting effect on the receiving neuron • The actual size of the weight controls the degree(程度) to which the corresponding input is allowed to inhibit or excite the receiving neuron.

  39. hidden input output 1 1 1.5 0.5 1 1 1 0 1 1 -2 1 1 0 1

  40. hidden input output 1 1 1.5 0.5 1 1 1 0 0.35 0 0 0 0.35 0 1

  41. the network configuration in figure 11.18 is far more simplistic than an actual biological network

  42. Training Artificial Neural Networks訓練類神經網路 • An important feature of artificial neural networks is that they are not programmed in the traditional sense(並非以傳統的思維來撰寫程式) but instead are trained(被訓練) – a programmer does not determine the values of the weights needed to solve a particular problem and the “plug”(插入) those values into the network.

  43. Instead, an artificial neural network learns the proper weight values via supervised training(監督式訓練) involving a repetitive process in which inputs from the training set are applied to the network and then the weights are adjusted by small increments so that the network’s performance approaches the desired behavior.

  44. It is interesting to note how genetic algorithm techniques have been applied to the task of training artificial neural networks. • In particular, to train a neural network, a number of sets of weights for the network can be randomly generated – each set of which will serve as a chromosome for the genetic algorithm. • Then, in a step-by-step process, the network can be assigned the weights represented by each chromosome and tested over a variety of inputs.

  45. The chromosomes producing fewest errors during this testing can then be given a greater probability of being selected as parents for the next generation. • In numerous experiments this approach has ultimately led to a successful set of weights.

  46. Let us consider an example in which training an artificial neural network to solve a problem has been successful and perhaps more productive than trying to provide a solution by means of traditional programming techniques. The problem is one that might be faced by a robot when trying to understand its environment via the information it receives from its video camera.

  47. Suppose, for example, that the robot must distinguish between the walls of a room, which are white, and the floor, which is black. • At first glance, this would appear to be an easy task: Simply classify the white pixels(圖素) as part of a wall and the black pixels at part of the floor. • However, as the robot looks in different directions or moves around the room, various lighting conditions can cause the wall to appear gray in some cases whereas in other cases the floor may appear gray. • Thus, the robot needs to learn to distinguish between walls and floor under a wide variety of lighting conditions.

  48. To accomplish this, we could build an artificial neural network whose inputs consist of values indicating(指出) the color characteristics(特性 ) of an individual pixel in the image as well as a value indicating the overall brightness of the entire image. • We could then train the network by providing it with numerous examples of pixels representing parts of walls and floors under various lighting condition.

More Related