Scribd
Upload
27 views9 pages

AI-ML Assignment

The document explains the differences between Artificial Intelligence (AI) and Machine Learning (ML), using self-driving cars as an example. It also discusses the types of AI, the Turing test, algorithms for various learning techniques, and compares Artificial Neural Networks (ANN) with Biological Neural Networks (BNN). Key concepts include the role of data in ML, the hypothetical nature of General AI and Superintelligence, and the operational differences between ANN and BNN.

Uploaded by

khyatishrimali712
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
27 views9 pages

AI-ML Assignment

The document explains the differences between Artificial Intelligence (AI) and Machine Learning (ML), using self-driving cars as an example. It also discusses the types of AI, the Turing test, algorithms for various learning techniques, and compares Artificial Neural Networks (ANN) with Biological Neural Networks (BNN). Key concepts include the role of data in ML, the hypothetical nature of General AI and Superintelligence, and the operational differences between ANN and BNN.

Uploaded by

khyatishrimali712
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/ 9

1) Difference between AI and ML and relat with example.

Ans.
AI ML
• Artificial intelligence (AI), • Machine Learning (ML)
where intelligence is means gaining skill
defined as the or knowledge.
acquisition of knowledge
and the ability to
apply knowledge.
• To create machines that • to teach machines to
and act like humans. learn form data and get
better at tasks over time.
• Use differen techniques • Use data to find patterns
like rules or learning to and make decision
solve problems. without being programed
for every step.
• Can be developed with • Required a lot of data to
or without data. train and improve.
• Artificial Intelligence is a • MLenables the system to
decision maker learn new things
from the data.

Exampal related to self driving car:


• AI imagine a self driving car the car needs to make
decisions like when to stop turn or speed up.
• ML the car learns from millions of images of roads, traffic
signs, and people to recognize what its seeing this is where
ml comes in.

2) Explain AI and elaborate with example of turing test.


Ans.
Artificial Intelligence (AI) is the development of computer
systems that can perform tasks that typically require human
intelligence.
Ai can be categorized into three main types:
1. Narrow AI (Weak AI): This is the most common type of AI
we encounter today. Narrow AI is designed to perform a
specific task or set of tasks. Examples include facial
recognition systems, virtual assistants like Siri and Alexa,
and self-driving cars.
2. General AI (Strong AI): This type of AI is hypothetical and
would possess the ability to understand, learn, and apply
knowledge across a wide range of tasks, just like a human.
We haven't achieved general AI yet.

3. Superintelligence: This is a hypothetical type of AI that


would surpass human intelligence in every aspect. It's a
concept often explored in science fiction and raises
significant ethical and philosophical questions.
The Turing test is a thought experiment proposed by Alan
Turing in 1950 to determine whether a machine can exhibit
intelligent behavior indistinguishable from that of a human.

The turing test:


1. Imagine a conversation between the evaluator, a human,
and a machine
2. Evaluator: "Tell me about your favorite book."
3. Human: "I love '1984' by George Orwell. It's a thought-
provoking novel about a dystopian future."
4. Machine: "I'm a big fan of 'Pride and Prejudice' by Jane
Austen. The characters are so well-developed."
5. In this example, both the human and the machine
provided responses that could have been made by a
human. If the evaluator were unable to consistently
differentiate between the two responses, the machine
would have passed the Turing Test.
So we can saythat AI can also think like human.
3) Flowchart for self driving car.
Ans. Start

Collect data from all sensors

Process data to remove noise

Identify No
the object

yes
Create a map of the surrounding
surrounding
Determine an optimal path to the destination

Genrate smooth and safe trajectoryes for vehicle

Control the vehicle with steering, throttle, break

Monitor vehicle state and enverment detect potential hazar and take decision

Provide information to the driver allow to control vehicle if need

End
Algorithm :-
Step 1 : Start While True:
Step 2 : # Sensor Data Acquisition
Collect data from all sensors (camera, LiDAR, radar, GPS, etc.)
Step 3 : # Data Processing
Process sensor data to remove noise and outliers Calibrate
sensor data
Step 4 : # Object Detection and Tracking
Identify and classify objects in the environment (cars,
pedestrians, traffic signs, etc.)
Step 5 : # Environment Mapping
Create a map of the surrounding environment (lanes, road
boundaries, obstacles)
Step 6 : # Path Planning
Determine the optimal path to the destination based on the
map and traffic conditions
Step 7 : # Motion Planning
Generate smooth and safe trajectories for the vehicle
Step 8 : # Vehicle Control Send commands to the vehicle's
actuators (steering, throttle, brakes) to follow the planned path
step 9 : # Monitoring and Control Monitor the vehicle's state
and environment Detect potential hazards and take appropriate
actions Handle unexpected situations
Step 10 : # Human-Machine Interface
Provide information to the driver (vehicle status, route,
warnings) Allow driver to take control if necessary
Step 11 : End While
End

4) List out algorithm for supervised, unsupervised and


reinforcement learning. Identify name of algorithm you can be
use for each learning techniques.
Ans.
Supervised learning algorithms are trained on labeled data to
learn a mapping function that can predict outputs for new,
unseen inputs.
Algorithm :
• Linear Regression
• Logistic Regression
• Decision Trees
• Random Forest
• Support Vector Machines (SVM)
• Neural Networks
Unsupervised Learning Algorithms are machine learning
techniques that learn patterns, structures, or relationships
within data without labeled outputs.
Algorithm :
• K-Means Clustering
• Hierarchical Clustering
• Principal Component Analysis (PCA)
• t-SNE
• Apriori Algorithm
• Isolation Forest
Reinforcement learning is a machine learning technique where
an agent learns to interact with an environment to maximize a
reward signal. The agent learns through trial and error, taking
actions and receiving feedback in the form of rewards or
penalties.
Algorithm :
• Dyna-Q
• Deep Q-Networks (DQN)
• Policy Gradient Methods
A versatile algorithm : A versatile algorithm is an algorithm that
can be applied to a wide range of problems or tasks,
demonstrating adaptability and flexibility in its use.
Supervised Learning:
• MLPS
• Logistic Regression
• Decision Trees
• RNNs
• Support Vector Machines (SVM)
• CNNs
Unsupervised Learning:
• Hierarchical Clustering
• Principal Component Analysis (PCA) t-SNE
• Apriori Algorithm
Reinforcement Learning:
• Q-Learning
• Deep Q-Networks (DQN)
• Policy Gradient Methods
• Actor-Critic Methods
5) comparison between ANN and BNN.
Ans.
Artificial neural Biological neural
network(ANN) network(BNN)
• It is the mathematical • It is composed of several
model which is mainly processing pieces known
inspired by the biological as neurons that are
neuron system in linked
the human brain. together via synapses
• Its processing was • It processes the
sequential and information in a parallel
centralized. and distributive manner..
• Its control unit keeps • All processing is
track of all computer- managed centrally.
related operations
• It processes the • It processes the
information at a information at a
faster speed. slow speed.
• It cannot perform • The large quantity and
complex pattern complexity of the
recognition. connections allow the
brain to perform
complicated tasks.
• It doesn't provide any • It provides feedback.
feedback.

You might also like