Scribd
Upload
14 views

AI

Uploaded by

D Vehu Alonge
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
14 views

AI

Uploaded by

D Vehu Alonge
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 3

1. What is Artificial Intelligence (AI)?

Artificial Intelligence (AI) is a branch of computer science focused on creating


machines capable of performing tasks that typically require human intelligence.
These tasks include problem-solving, reasoning, learning, understanding natural
language, and perception. AI involves developing algorithms and models that enable
computers to simulate cognitive functions such as learning from experience and
adapting to new inputs.
2. What is AI concerned with?

AI is primarily concerned with the development of intelligent systems that can:

Learn from data (machine learning).


Make decisions based on data (reasoning and logic).
Solve complex problems efficiently.
Understand and process natural language.
Perceive the environment through sensors (e.g., computer vision, speech
recognition).
Interact with humans and other systems autonomously.

3. What is learning, and reasoning in the context of AI?

Learning in AI: Refers to the ability of a machine or algorithm to improve its


performance on a task over time by gaining experience from data. This can be
achieved through methods such as supervised, unsupervised, or reinforcement
learning.

Reasoning in AI: Involves the ability of a machine to solve problems and make
decisions based on logic and knowledge. This includes deductive reasoning (deriving
conclusions from known facts) and inductive reasoning (inferring general rules from
specific examples).

4. Enumerate three (3) Applications of AI.

Healthcare: AI is used for diagnosing diseases, drug discovery, and


personalized treatment plans through analyzing medical data and imaging.

Autonomous Vehicles: AI powers self-driving cars by processing sensor data,


making decisions, and controlling the vehicle autonomously.

Natural Language Processing (NLP): AI enables machines to understand,


interpret, and generate human language, as seen in virtual assistants (e.g., Siri,
Alexa) and chatbots.

5. List the Brute-Force Search Methods you know, and explain any two (2) of them.

Breadth-First Search (BFS): Explores all nodes at the present depth level
before moving on to nodes at the next depth level. It systematically searches level
by level, ensuring that all possible paths are considered. BFS guarantees the
shortest path in an unweighted graph but can be slow and memory-intensive.

Depth-First Search (DFS): Explores as far as possible along one branch before
backtracking to explore others. It uses a stack-based approach and is memory-
efficient compared to BFS but may not find the shortest path in unweighted graphs.

Other brute-force methods include:

Uniform Cost Search (UCS)


Iterative Deepening Search (IDS)
6. What are the divisions that have characterized the Evolution of Artificial
Intelligence (AI)?

The evolution of AI is generally divided into the following phases:

Symbolic AI (Good Old-Fashioned AI - GOFAI): In the early days of AI,


researchers focused on symbolic reasoning, rule-based systems, and logic-based AI
models.

Statistical AI (Machine Learning Revolution): This phase emphasizes data-driven


approaches where statistical models and algorithms (e.g., neural networks, decision
trees) learn from data rather than relying on pre-programmed rules.

Deep Learning and Neural Networks: Modern AI is driven by deep learning


techniques that allow for the development of complex models capable of recognizing
patterns and making predictions, particularly in areas like computer vision and
natural language processing.

7. List the Informed Search Methods you know.

Informed search methods include:

A* (A-star) Search
Greedy Best-First Search
Best-First Search
Iterative Deepening A* (IDA*)
Bidirectional A*
Beam Search
Memory bounded A Search
Weighted A

8. Briefly explain the three (3) Types of AI.

Artificial Narrow Intelligence (ANI): Also known as Weak AI, this type is
specialized in a single task and operates under a limited set of conditions.
Examples include facial recognition systems and virtual assistants.

Artificial General Intelligence (AGI): Also known as Strong AI, AGI refers to
machines that have the ability to understand, learn, and apply intelligence across
a wide range of tasks, similar to human cognitive abilities. This is still
theoretical and has not been achieved.

Artificial Superintelligence (ASI): This type would surpass human intelligence


in all aspects, including creativity, general wisdom, and problem-solving. ASI is
speculative and represents a potential future scenario.

9. When is a Heuristic admissible?

A heuristic is considered admissible if it never overestimates the cost of reaching


the goal from the current state. In other words, it is optimistic and guarantees
that the path it suggests is the most cost-effective or shortest. Admissible
heuristics are important in algorithms like A* to ensure optimality.
10. Define the following concepts:

i. Frames: Frames are data structures used in AI to represent stereotyped


situations or concepts. They organize knowledge into slots (attributes or
properties) and values (details about the attributes), allowing the system to
reason about entities in the world.

ii. Scripts: Scripts are structured representations of sequences of events or


actions in particular contexts. They describe what typically happens in a certain
situation, enabling AI systems to predict or infer missing information.

iii. Conceptual Graphs: These are graphical notations used to represent


knowledge. They depict concepts and their relationships in a form that is easy to
understand and process. Conceptual graphs are used in natural language
understanding and reasoning.

iv. Conceptual Dependency: Conceptual dependency is a theory used for


representing the meaning of natural language sentences. It focuses on breaking down
sentences into primitive actions and relationships between concepts to understand
the underlying meaning.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy