CS607 Final Term Subjective by Arshad and Asif

What is hypothesis space?

Answer: The hypothesis space used by a machine learning system is the set of all hypotheses that might possibly be returned by it. It is typically defined by a hypothesis language, possibly in conjunction with a language bias.

Q2. What is machine learning?

Answer: (Page 160) Generally speaking, the goal of machine learning is to build computer systems that can learn from their experience and adapt to their environments. Obviously, learning is an important aspect or component of intelligence.

Q3. What is a strip?

Answer: (Page 197) STRIP is one of the founding languages developed particularly for planning. Let us understand planning to a better level by seeing what a planning language can represent.

Q4. What is differing between height and depth of a tree?

Height and depth of a tree is equal but height and depth of a node is not equal because the height is calculated by traversing from leaf to the given node depth is calculated from traversal from root to the given node.

Ϯ. What do you kŶoǁ aďout MaŵdaŶi’s fuzzy iŶfereŶĐe ŵethod?

Answer: (Page 153)

Mamdani's fuzzy inference method is the most commonly seen fuzzy methodology. Mamdani's method as among the first control systems built using fuzzy set theory. It was proposed in 1975 by Ebrahim Mamdani as an attempt to control a steam engine and boiler combination by synthesizing a set of linguistic control rules obtained from experienced human operators. Mamdani's effort was based on Lotfi Zadeh's 1973 paper on fuzzy algorithms for complex systems and decision processes.

What is the basic key of candidate elimination algorithm?

Answer: (Page 173)

Predicate action?

Answer: (Page 198)

Action is a predicate used to change states. It has three components namely, the predicate itself, the precondition, and post-condition predicates. For example, the action to buy something item can be represented as,

Action:

buy(X)

Pre-conditions:

at(Place)

Post-conditions/Effect:

have(X)

Differ between supervised and unsupervised learning? 5 marks

Unsupervised Learning

• The ŵodel is Ŷot pƌoǀided ǁith the ĐoƌƌeĐt ƌesults duƌiŶg the tƌaiŶiŶg.
• CaŶ ďe used to Đlusteƌ the iŶput data iŶ Đlasses oŶ the ďasis of theiƌ statistiĐal pƌoperties only.
• Clusteƌ sigŶifiĐaŶĐe aŶd laďeliŶg.
• The laďeliŶg ĐaŶ ďe Đaƌƌied out eǀeŶ if the laďels aƌe oŶlLJ aǀailaďle foƌ a sŵall Ŷuŵďeƌ of oďjeĐts representative of the desired classes.

Supervised Learning

• TƌaiŶiŶg data iŶĐludes ďoth the iŶput and the desired results.
• Foƌ soŵe edžaŵples the ĐoƌƌeĐt ƌesults ;taƌgetsͿ aƌe kŶoǁŶ aŶd aƌe giǀeŶ iŶ iŶput to the ŵodel during the learning process.
• The ĐoŶstƌuĐtioŶ of a pƌopeƌ tƌaiŶiŶg, ǀalidatioŶ aŶd test set ;BokͿ is ĐƌuĐial.
• These ŵethods aƌe usually fast and accurate.
• Haǀe to ďe aďle to geŶeƌalize: giǀe the ĐoƌƌeĐt ƌesults ǁheŶ Ŷeǁ data aƌe giǀeŶ iŶ iŶput ǁithout knowing a priori the target.

What are the linear separable line and non linear separable line?5

Answer: (Page 184)

There is a whole class of problems which are termed as linearly separable. This name is given to them, because if we were to represent them in the input space, we could classify them using a straight line. The simplest examples are the logical AND or OR. We have drawn them in their input spaces, as this is a simple 2D problem. The upper sloping line in the diagram shows the decision boundary for AND gate, above which, the output is 1, below is 0. The lower sloping line decides for the OR gate similarly.

A single perception simply draws a line, which is a hyper plane when the data is more than 2 dimensional. Sometimes there are complex problems (as is the case in real life). The data for these problems cannot be separated into their respective classes by using a single straight line. These