Scribd
Upload
10 views8 pages

Sadarus Assingment

Uploaded by

Kamal Suren
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
10 views8 pages

Sadarus Assingment

Uploaded by

Kamal Suren
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

Task 01

[01]
Machine Learning in AI
Application:-
Machine learning (ML) is widely used in various applications within AI, such as

1. Image and Speech Recognition:-ML algorithms are employed for image and speech
recognition tasks, enabling systems to identify and interpret visual and auditory data.
2. Recommendation Systems:- ML is used in recommendation engines for suggesting
products, movies, or content based on user preferences and behavior.
3. Natural Language Processing (NLP):-ML models power language translation, sentiment
analysis, and chatbots, enhancing human-computer interactions.
4. Fraud Detection:- ML algorithms can detect patterns and anomalies in financial
transactions, aiding in the identification of potential fraud.

Data Dependency:- ML models heavily rely on the quality and quantity of training data. Biased
or inadequate datasets can lead to biased models or poor performance.
Interpretability:- Many ML models, especially complex ones like neural networks, lack
interpretability. Understanding the decision-making process of these models is challenging.
Overfitting:- There's a risk of overfitting, where a model performs well on training data but fails
to generalize to new, unseen data.

Deep Learning in AI
Application:-
Deep learning (DL), a subset of ML, involves neural networks with multiple layers and is
applied in various domains.

1. Computer Vision:- Deep learning excels in image and video analysis tasks, such as object
detection, image classification, and facial recognition.
2. Natural Language Processing:- DL models like recurrent neural networks (RNNs) and
transformers are used for language translation, text generation, and sentiment analysis.
3. Speech Recognition:- Deep learning techniques are employed in speech recognition
systems, enabling voice commands and transcription.
4. Autonomous Vehicles:- Deep learning plays a crucial role in the development of self-
driving cars, enabling them to perceive and respond to the environment.
Computational Intensity: Training deep learning models can be computationally intensive and
requires specialized hardware, making it resource-intensive.
Data Hunger: Deep learning models often require large amounts of labeled data for training,
which may be a limitation in some domains.
Lack of Interpretability: Deep neural networks, especially deep convolutional networks, can be
challenging to interpret, leading to a lack of transparency in decision-making.

Self-Driving Vehicle Technology


Application:-
Self-driving vehicle technology involves AI techniques to enable vehicles to operate
autonomously.

1. Computer Vision:- Cameras and sensors on vehicles use computer vision algorithms to
perceive the surrounding environment.
2. Sensor Fusion:- Integrating data from various sensors, including LiDAR and radar, to
create a comprehensive understanding of the vehicle's surroundings.
3. Path Planning:- AI algorithms are used to plan the optimal path for the vehicle,
considering traffic conditions, obstacles, and safety.
4. Machine Learning for Decision-Making:- ML is employed for decision-making tasks,
such as predicting the behavior of other road users and adapting to dynamic situations.

Safety Concerns: Ensuring the safety of self-driving vehicles, especially in complex and
unpredictable environments, remains a significant challenge.
Regulatory Challenges: The legal and regulatory framework for autonomous vehicles is still
evolving, and addressing issues related to liability and standards is crucial.
Ethical Dilemmas: AI-driven decision-making in critical situations raises ethical questions, such
as how vehicles should prioritize the safety of occupants versus pedestrians.
[02]
1. Coursera: Machine Learning by Andrew Ng
Type: Paid (Audit for free, but certification is paid)
Strengths: Taught by a renowned expert, provides a solid foundation in machine learning.
Weaknesses: Some learners find it more theoretical, and the programming assignments may
require a good understanding of linear algebra and calculus.
2. edX: Introduction to Artificial Intelligence (AI) by Microsoft
Type: Paid (Audit for free, but certification is paid)
Strengths: Developed by Microsoft, covers both basic and advanced AI concepts.
Weaknesses: Some learners find the content to be less interactive compared to other platforms.
3. Udacity: Deep Learning Nanodegree
Type: Paid
Strengths: Hands-on projects and mentor support. Focuses on practical applications of deep
learning.
Weaknesses: Relatively expensive compared to some other platforms.
4. Google's Machine Learning Crash Course
Type: Free
Strengths: Developed by Google, covers a wide range of ML concepts with practical examples.
Weaknesses: Some users find it to be more of an introductory course.
5. Stanford University: CS231n - Convolutional Neural Networks for Visual
Recognition
Type: Free
Strengths: In-depth coverage of Convolutional Neural Networks (CNNs) for image recognition.
Weaknesses: Assumes a certain level of background in machine learning and programming
6. MIT Open Courseware: Introduction to Deep Learning
Type: Free
Strengths: MIT-level quality content covers fundamentals of deep learning.
Weaknesses: May be more challenging for beginners without prior exposure to machine
learning.
[03]
Task 02
[01]
[02]
[03]
[04]
(4.1)

You might also like