1. LEARNING MODEL FOR CONSTRUCTION OF THE BEST DECISION SEQUENCE USING PRIOR KNOWLEDGE Thesis Presentation by Lilit Yenokyan

2. PROBLEM STATEMENT The task of this thesis is development of a learning system capable of learning from prior solution instances of a problem and able of developing new solution procedures when similar problem is introduced to the system. System involves multiple decision makers and multiple decision sequences.

3. PROBLEM STATEMENT (cont.) Applications Medical Field Product Assembly Assisting Drivers in Navigation Other tasks presented in the terms of system (Decision Makers, Decision sequences)

4. Stages of the Approach Constructing the Knowledge Base 1. Initial approach builds a learning system to document the steps of decision sequences in problem solving and also information/data used for decision making. 2. Directed Acyclic Graph (DAG) is used to represent these decision sequences, where the nodes in the graph represent the actions taken by the problem solver and directed edges represent the order of the decisions (steps). 3. In mathematics DAG, is a directed graph with no directed cycles; such that, for any vertex v, there is no nonempty directed path that starts and ends on v.

5. Stages of the Approach Finding the Best Decision Sequence 1. Dynamic programming approach is proposed to quickly examine various solution alternatives documented in DAG and develop as new improved solution for the problem. 2. The notion of best solution is based on the problem and the application, e.g. shortest completion time, shortest distance traveled, least load or cost required and so on.

6. Available Learning Models Artificial Intelligence Agent – the actor in the system. Multi-agent Systems Cooperative Concurrent Supervised Correct output is provided to system. Unsupervised Ability of recognize patterns in streams of input Reinforcement Reward for correct decisions, punishment for incorrect decisions Semi-Supervised Learning Combination of Supervised and Unsupervised Learning

7. Available Learning Models (cont.) Neural Networks Inspired and modeled based on brain neurons. Feed-Forward Recurrent Neural Networks Decision Trees Classification Learning. Every branch is a chose between a number of alternatives, and each leaf node represents a classification or decision. Explanation Based Learning Uses learning model of an example is sufficient for learning. Relevance Based Learning Generalizes the information from prior knowledge and uses hypothesis to create new learning examples

8. Differences and similarities Our approach includes elements of Reinforcement Learning Semi-Supervised Learning Decision Trees Using Methods: Graph Theory Dynamic programming

9. Notations

10. Types of nodes Knowledge base presented as Directed Acyclic Graph with distinct types of nodes NodeSets and Regular Nodes is called Hypertree.

11. Introducing concept of NodeSet Decision that results from merging nodes i1 and i2 with attribute x, is the outcome A

12. Decision that results from merging nodes i3 and i4 with attribute y, is the outcome A Introducing concept of NodeSet (cont.)

13. NodeSet notation used to illustrate the case: and. Introducing concept of NodeSet (cont.)

14. Example – Two Decision sequences First Decision Sequence

15. Second Decision Sequence Example – Two Decision sequences

16. Theory and Algorithms

17. Knowledge Base Construction Algorithm Decision made by DM N, where A is resulting decision {e 1, …, e n } are the decision at the input that produce A, {a} is the attribute value of the decision. Decision sequence of decision maker N. NodeSet in the Hypertree, where A is resulting intermediate or final entity, {e 1, …, e n } are the basic or intermediate entities at the input that produce A, {a} is the attribute value of the nodeSet.

18. Input: Set of decision sequences Step 3: For each entity e i in {e 1, …, e n } do: If e i is not in H_Tree then add new node e i to H_tree Endfor If A is not in H_Tree then add new node A to H_tree Add new nodeSet to H_tree, with references to resulting node {A} and entity nodes {e 1, …, e n } and attribute value {a}. Step 2: For each decision sequence DS m where m = 1, 2,...,S For each decision in decision sequence DS m do: Goto Step 3 Endfor Return H_Tree Knowledge Base Construction Algorithm Output: Hypertree of knowledge base H_tree Step 1: Initialize H_tree=Ø

19. Example – Constructing Hypertree Hypertree Build based on two decision sequences

20. Example – KBC (Step 1) First decision of the blue decision sequence

21. Example – KBC (Step 2) Second decision of blue decision sequence

22. Example – KBC (Step 3) Final decision of blue decision sequence

23. Example – KBC (Step 4) First decision of the green decision sequence

24. Example – KBC (Step 5) Second decision of green decision sequence

25. Example – KBC (Step 6) Final decision of the green decision sequence

26. Example – Constructing Hypertree Constructing Knowledge Base – Complete

27. Best Decision Sequence where: BDS is Best Decision Sequence, N is the number of nodeSets for the entity node A, NodeSet ns i is the i-th nodeSet of node A, a i is the attribute value of nodeSet ns i, {e j } is the j-th entity node in nodeSet ns i resulting to A, and m is the number of decisions sequences that result to A by nodeSet ns i.

28. Step 2: Calculate BDS for all the solution sequences For each outcome sequence where n = 1, 2,...,m Calculate and store End For Algorithm 2- Construction of Best Decision Sequences for List of Outcomes Input: Set of decisions to examine: Output: Best solution sequence for each final outcome in Out_set Step 1: Initialize array of solution paths Des_array[1,..,m] = Ø Step 3: Return Des_array[1,..,m]

29. Algorithm 3- Best Decision Sequence Input: Node A Output: Best Decision Sequence Step 1: If BDS(A) has already been calculated then return BDS(A) Step 2: Initialize: current_value = +branch_value = + Step 3:for each NodeSet of node A do Set branch_value = {a} + branch_value = min(current_value, branch_value) Record index k, from {e k } which minimized current_value Endfor Step 4:Return BDS(A)

30. Example – Illustration of Algorithm 2 & 3 Given the Hypertree from the previous example extended with new Decision sequence: i 6, i 7 Solution 3 (14) Construction of Best Decision Sequences (Algorithm 2) is called with {Solution 1, Solution 2, Solution 3} on its input

31. Example – BDS Solution 3

32. Example – BDS Solution 1

33. Example – BDS Solution 1 (Step 1)

34. Example – BDS Solution 1 (Step 2)

35. Example – BDS Solution 1 (Step 3)

36. Example – BDS Solution 1 (Final)

37. Example – BDS Solution 2

38. Example – BDS Solution 2 (Step 1)

39. Example – BDS Solution 2 (Step 2)

40. Example – BDS Solution 2 (Step 3)

41. Example – BDS Solution 2 (Step 4)

42. Example – BDS Solution 2 (Final)

43. Applications and Examples

44. Medical Application Input - Various sequences of tests prescribed by doctors for patients with similar symptoms and their final diagnoses Goal - Identify the best sequence of tests for developing accurate diagnosis of patients with certain symptoms. Sequence is based on specified criteria. Criteria - Cost, accuracy, lead time to diagnose

45. Product Assembly Application Input - Various feasible assembly sequences are captured in a knowledge base. Goal – Construct assembly sequence based on sequences given at the input optimal with respect to certain criteria. Criteria – Assembly time, cost, number of setups

46. Assisting Drivers Finding Best Driving Directions Application Input - various driving routes between the origin and destination. Goal - examine those routes and produce a new path that is optimal with respect to specific criteria Criteria - time, distance traveled, cost of gas

47. Medical Application Study involves medical history of group of patients with the similar initial symptoms and complains. It is possible that during the examination of the patient several doctors prescribe different tests but arrive to same conclusion.

48. Medical Application Consider the diagnostic history of patients with similar symptoms. The history of symptoms and diagnoses are documented for the patients and later the patients are divided by a medical professional to groups of people who had similar symptoms. During the examination of a patient from a group, every test prescribed by the doctor is recorded, doctor also supplies the system all the possible conclusions or intermediate decisions he/she makes based on results of each test.

49. Medical Application Operation is performing the test Initial entities in the knowledge base model are medical tests Intermediate entities are the decisions of doctors based on initial tests Final entities are final diagnoses.

50. Medical Application Construction of knowledge base for tests prescribed for patients with similar symptoms

51. Medical Application Construction of Best Decision Sequence for Diagnosis 1 and Diagnosis 2

52. Medical Application Diagnosis 1 - Comparing values (costs) of checking a patient against Diagnosis 1 is 11 versus initial costs 15 and 13. This is an improvement of 15% percent of the initial cost. Diagnosis 2 - The value for checking a patient against Diagnosis 2 is the same as it was initially 15.

53. Medical Application System is intended to assist the medical professional not replace. In the case if during patient inspection doctor decides to examine a diagnosis that is not in the knowledge base, the learning system records new diagnosis and the tests prescribed by the doctor for checking it. At any step if a test results do not satisfy the condition and diagnose k should not be considered any longer, sequence for performing the tests stops, as negative decision about diagnosis k has been reached.

54. Assembly Application Given all the necessary mechanical parts of the desk, a number of professionals are assigned to independently assemble it. The professionals perform the assembly in various orders requiring various amounts of time. The assumption is that each professional has same level of competency and that the time required performing a certain task is the same for all of them. The time of each action performed is available, i.e. system is tracking the time it takes the professional to perform each step of assembly.

55. Assembly Application Operation in the application is joining several parts of product together. Basic entities in the knowledge base are the parts of the final product. Intermediate entities are subassemblies obtained by sequence of operations. Final entity is the assembled product. In this assembly example desk is the final entity.

56. Assembly Application

57. RED LINE 1) A, B AB (2) 2) C, AB ABC (2) 3) D, ABC ABCD (4) 4) K, F KF (3) 5) G, KF KFG (6) 6) H, GKF KFGH (6) 7) L, E EL (5) 8) EL, KFGH Drawer (5) 9) M, ABCD ABCDM (7) 10) N, ABCDM Table (7) 11) Table, Drawer Desk (6) Total: 53 minutes

58. Assembly Application GREEN LINE 1) A, M AM (2) 2) C, N CN (2) 3) AM, B ABM (2) 4) CN, ABM ABCNM (2) 5) D, ABCNM Table (5) 6) F, K KF (3) 7) H, FK KFH (3) 8) G, KFH KFGH (5) 9) E, KFGH Drawer_no_handle (2) 10) Drawer_no_handle, Table Desk_no_handle (6) 11) L, Desk_no_handle Desk (14 ) Total: 47 minutes

59. Assembly Application BLUE LINE A, M AM (2) 2) C, N CN (2) 3) D, AM ADM (2) 4) ADM, CN ACDNM (3) 5) B, ACDNM Table (1) 6) F, K KF (3) 7) G, KF KFG (6) 8) H, KFG KFGH (6) 9) L, E EL (5) 10) Table, KFGH Desk_no_front (4) 11) Desk_no_front, EL Desk (11) Total: 45 minutes

60. Assembly Application

61. blue green red 1) A, M AM (2) 2) C, N CN (2) 3) D, AM ADM (2) 4) ADM, CN ACDNM (3) 5) B, ACDNM Table (1) 6) F, K KF (3) 7) H, FK KFH (3) 8) G, KFH KFGH (5) 9) L, E EL (5) 10) EL, KFGH Drawer (5) 11) Table, Drawer desk (6) Total: 37 minutes

62. Deadlock Elimination

63. Software Screenshot (Desk Assembly)

64. Research at the UofM Dearborn

65. Mirror symmetric reconstruction and Matching 1. Right leg 2. Left leg missing patella 3. Mirror reconstructed left leg 4. Generated mesh for missing sections 5. Zoomed view

66. 1. Right ribs2. Left ribs 5 th rib broken 3. Mirror reconstructed left ribs 4. Generated mesh for missing rib 5. Generated solid Mirror symmetric reconstruction and Matching

67. Partial Symmetry Reconstruction 1. Right hand damaged middle finger2. Damaged area intersection with box3.Middle finger separate view in box 4. Candidate reconstruction area5. Damaged bone view6. Reconstructed finger bone

68. Density Analysis – Damage Area Recognition 1. Ulna bone 2.Ulna vertex mapping 3. Ulna edges mapping 4. Left ribs 5th rib broken 5. Left ribs vertex mapping 6. Left ribs edges mapping

69. Thank you! Questions and Answers