Scribd
Upload
9 views6 pages

All Complete

Uploaded by

Ahmed Kamal Mohammed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views6 pages

All Complete

Uploaded by

Ahmed Kamal Mohammed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

2019

• -------- a sentence can be parsed in different ways. Answer:


Ambiguity

• Word tokenization is performed using ------------------------- function.


Answer: word_tokenize()

• To select the words starting with a capital letter we use the following
code -------- Answer: Tokenization - Tokenize()

• -------- a specific representation learned from data by applying


machine learning. Answer: Model

• -------- is an individual measurable property of our data. Answer:


Feature

• ------ is the task to find the distribution of inputs in some space.


Answer: Density estimation

• ------ is a type of problem where we need to predict the continuous


value. Answer: Regression

• treebank.parsed_sents('wsg.mrg')[0] is used for


……………………………… Answer: Classification

• ------ is a study of words formation and their relationship with each


other. Answer: Morphology

• Agents are able to operate without the guidance of human beings is


called ........ Answer: Autonomous
2020
• In an Unsupervised learning specific output values are not provided.

• The function of Supervised Learning are prediction, classification,


regression.

• Rationality: a property of agents that choose actions that maximize


their expected utility.

• Overfitting in Machine Learning means a model has a poor


performance, memorizes the training data and performs poorly on
unseen data.

• The meaning of Corpus in natural language processing is a large


collection of text used for NLP tasks.

• Corpus: a model might look at the input data and try to predict labels
like "sick" or "healthy."

• TensorFlow: an open-source Python library written for constructing


neural networks and machine learning.

• TensorFlow can handle deep neural networks for image recognition,


handwritten digit classification.

• NumPy: is linear algebra developed in Python.

• Pandas: is an open-source library that offers a wide range of tools for


data manipulation & analysis.
1. The
2021
depth-first search method takes less memory.

2. Uninformed search is based on the best-first search method.

3. If the number of distinct percepts and actions is limited, the environment is


an intelligent agent, otherwise it is not.

4. TensorFlow is an open-source Machine Learning library. It is a fast, flexible, and


low-level toolkit for doing complex algorithms.

5. A model-based agent is an agent that has clear preferences, models uncertainty,


and that performs the right actions always.

6. Image Analysis works in a deterministic environment that is completely


described by the current state and the agent's action.

7. To extract the meaning from the group of sentences, semantic analysis is used.
(true)

8. A dataset is standardized into a tabular format with numerous rows and


columns, making it easier to store and process for analysis and machine learning
algorithms.

9. Text mining is responsible for analyzing text documents and classifying them
based on predefined topics.

10. Tokenization is the process of turning a meaningful piece of data into smaller
units.
1.
2022
............... is the process of breaking text up into smaller chunks as per our requirements.
Answer: Tokenization

2. We can generate frequency distribution of words in a corpus by using .... function.


Answer: NLTK

3. --- and --- are the two main problems that can be solved with Supervised Machine
Learning.
Answer: Classification and Regression

4. To remove the Punctuation by using NLTK, you have to use ........................................


Answer: string.punctuation or nltk.tokenize.word_tokenize with filtering

5. NLTK has different stemmers which implement different methodologies such as ........, ........
Answer: Porter Stemmer, Lancaster Stemmer, Snowball Stemmer

6. The rational agent at any given time depends on four things ........, ........, ........, ........
Answer:
o The agent’s performance measure.
o The agent’s internal state.
o The agent’s actions.
o The agent’s percepts.

7. ..... is an agent whose action depends only on the current percept.


Answer: Simple reflex agent

8. .... the Process of reducing the size of the tree by removing the nodes which play a minimal
role.
Answer: Pruning

9. Random forest is used in many applications such as ...............


Answer: Classification, Regression, Feature Selection

10. ..... acts to maximize the expected value of the performance measure.
Answer: Rational agent
2023
1. An action is something that the agent can choose to do.

2. The Successor Function describes the agent's options: given a state, it returns a set
of actions.

3. The performance measure evaluates the behavior of the agent in an environment. A


rational agent acts so as to maximize the expected value of the performance
measure.

4. The rational agent at any given time depends on four things:


o The agent’s performance measure.
o The agent’s internal state.
o The agent’s actions.
o The agent’s percepts.

5. A task environment specification includes the performance measure, the external


environment, the actuators, and the sensors.

6. Search algorithms are judged on the basis of:


o Completeness.
o Optimality.
o Time complexity.
o Space complexity.

7. Informed search may have access to a heuristic function that estimates the cost of a
solution from a node.

8. The Random Forest algorithm can be used in both classification and regression.

9. The main challenge/s of NLP is/are: ambiguity and complexity.

10. Morphological segmentation is used to separate words into individual morphemes.


1.
2024
........ is a graph whose nodes are the set of all states, and whose links are actions that
transform one state into another.
Answer: State space

2. ......... happens when two related words should be reduced to the same stem but aren't.
Answer: Stemming

3. ...... happens when a data model is unable to capture the relationship between the input
and output variables accurately, generating a high error rate on both the training set and
unseen data.
Answer: Underfitting

4. More than one dependency parse trees are known as…….


Answer: Ambiguous

5. Stemming is a text processing task in which you reduce words to their…...


Answer: Root form (or stem)

6. A .......... is an agent whose action depends only on the current percept (input).
Answer: Simple reflex agent

7. There are many ways of avoiding over-fitting such as………


Answer: Regularization (adding constraints to the model), data augmentation (increasing the
training data variety), and early stopping (stopping training before the model overfits).

8. Decision tree algorithm falls under the category of ……. learning.


Answer: Supervised

9. A ......... acts to maximize the expected value of the performance measure.


Answer: Rational agent

10. A ........... agent is an agent that selects actions that it believes will achieve explicitly
represented goals.
Answer: Goal-based

You might also like