Differences

This shows you the differences between two versions of the page.

--- public:t-720-atai:atai-22:engineering_assignment_2 [2022/10/08 00:28] – [Your Task:] arash
+++ public:t-720-atai:atai-22:engineering_assignment_2 [2024/04/29 13:33] (current) – external edit 127.0.0.1
@@ Line 7: / Line 7: @@
 ====Engineering Assignment 2:====
-===== Knowledge Transfer Via OpenNARS for Applications (ONA)=====
+===== Knowledge Transfer in OpenNARS for Applications (ONA)=====
 \\
@@ Line 34: / Line 34: @@
 Deriving an applicable behavior from the presence of a property:
 https://github.com/opennars/OpenNARS-for-Applications/blob/master/examples/nal/door2.nal
-And maybe diagnostics examples: (these will soon also work effectively when there are dozens of properties assigned to each instance)
-https://github.com/opennars/OpenNARS-for-Applications/blob/master/examples/nal/diagnostic.nal
 A more advanced example, numerical comparison carried out by NARS, with induction of a related behavior:
@@ Line 44: / Line 41: @@
 https://github.com/opennars/OpenNARS-for-Applications/blob/master/examples/nal/greenplant.nal
-If instead of cases showing the inference capabilities you want an environment where an agent shows knowledge transfer while operating, I will soon have more on that.
+If instead of cases showing the inference capabilities you want an environment where an agent shows knowledge transfer while operating, the ONA team will soon have more on that. This is something that usually demands goals in a domain to change, or behaviors to learn which generalize to new instances to be shown effectively.
-This is something that usually demands goals in a domain to change, or behaviors to learn which generalize to new instances to be shown effectively.
 An example here is https://github.com/opennars/OpenNARS-for-Applications/blob/master/examples/nal/example4.nal
-which corresponds to the following experiment which I initially made work with OpenNARS: https://www.youtube.com/watch?v=e92RV1BBeKU
+which corresponds to the following experiment: https://www.youtube.com/watch?v=e92RV1BBeKU
 ==== How to build ONA on your system ====
@@ Line 56: / Line 52: @@
 \\
-==== Your Task: ====
+==== Your Tasks ====
-Your task is to use what you learn from the above slides and examples in order to create three examples where the knowledge transfer capability of ONA can be shown according to the following instructions.
+Your task is to use the following instructions and what you learn from the above slides and examples in order to create three other examples where the knowledge transfer capability of ONA can be shown and evaluated.
-**1. Knowledge transfer via shared properties**. Your first task is to write a set of narsese statements that emulate three objects (a sphere, a cube and a cylinder) and a robotic hand that can grab the objects. Each object has three different properties including color, weight, and softness. The objects might have shared properties, e.g. both the cube and the sphere can have a blue color. Assign the properties to the objects such that the cube has more similarities to the sphere than to the cylinder. Then, give ONA causal knowledge that if it grabs the cube, the hand will be holding the cube. Now, you should ask ONA if it can grab (and then hold) the other two objects, i.e. if the hand applies a grab operation to the sphere/cylinder whether the hand will be holding the sphere/cylinder.
+**1. Knowledge transfer via shared properties**. Your first task is to write a set of narsese statements that emulate a task-environment where there exist three objects (a sphere, a cube and a cylinder) and a robotic hand that can //grab// the objects. Each object has three different properties including color, weight, and softness. The objects might have shared properties, e.g. both the cube and the sphere can have a blue color. Assign the properties to the objects such that the cube has more similarities to the sphere than to the cylinder. Then, give ONA the causal knowledge that if it //grabs// the cube, the hand will be //holding// the cube. Now, you should ask ONA if the hand can grab (and then hold) the other two objects, i.e. if the hand applies a //grab// operation to the sphere/cylinder whether the hand will be //holding// the sphere/cylinder.
 Now, write your analysis by focusing on how different the two answers created by ONA are, and how the similarity between the objects affects ONA's reasoning and knowledge transfer.
@@ Line 72: / Line 68: @@
 |  {{/public:t-720-atai:atai-22:analogy.png?1000}}  |   |
-First, implement all the relations of the Rutherford atom model, MoreMassiveThan, Attracts, and RevolevesAround, between the electron and the nucleus. Note that the relation nucleus MoreMassiveThan electron leads to the relation nucleus Attracts electron, which itself leads to the relation electron RevolvesAround nucleus. As shown in the figure, the same relations exist in the solar system, between the earth and the sun. Now, after giving ONA the information about the relations sun MoreMassiveThan earth and sun Attracts earth, ask ONA if can infer earth RevolvesAround sun.
+First, give information to ONA about all the relations in the Rutherford atom model, //MoreMassiveThan//, //Attracts//, and //RevolevesAround//, between the electron and the nucleus. Remember to allow ONA to know that the relation **nucleus //MoreMassiveThan// electron** leads to the relation **nucleus //Attracts// electron**, which itself leads to the relation **electron //RevolvesAround// nucleus**. As shown in the figure, the same relations exist in the solar system, between the earth and the sun. Now, after giving ONA the information about the relations **sun //MoreMassiveThan// earth** and **sun //Attracts// earth**, ask if it can infer **earth //RevolvesAround// sun**.
 Write your analysis after receiving ONA's answer by focusing on how effective ONA is in capturing the same relations between two processes.
-Allow ONA to know that earth is a planet. Now, ask ONA if a planet RevolvesAround sun. How different is the answer?
+Allow ONA to know that earth is a planet. Now, ask if the relation **planet //RevolvesAround// sun** holds. How different is the answer?
+Add some properties to the sun, e.g. sun is yellow and hot. Then, check how that influences the answer.
 (Bonus point) Try to play with the example so that you find the circumstances where ONA fails to correctly infer the correct relations. Write your analysis about that.
+**3. Knowledge transfer via comparison**.
+Your third task is to write a set of narsese statements that give ONA the names and the relative height of three boys. The names are John, Tom, and Karl. Tom is taller than John, and Karl is taller than Tom. Also, give ONA the knowledge that Tom can play basketball. Now, ask ONA if it can infer whether John and Karl can also play basketball.
+How different are the inferred basketball-playing abilities of John and Karl? Do an analysis regarding how ONA's knowledge transfer through comparison can be improved.
+**Note**: Please attach your *.nal files for each task when handing in the assignment.