1. SCHOOL OF SCHOLARS ,AKOLA
CLASS - VII (A)
SUBJECT ENRICHMENT ACTIVITY
GROUP NAME -> The Visionaries
GROUP MEMBERS :- 1)SANSKAR SAKHARE
2)PARTH KADODE
3)DARSHEEL CHARPE
4)KRISHNA BHATKAR
5)ARNAV DHOOT
Subject -> COMPUTER
2. Introduction to Machine Learning
What is Machine Learning?
Machine learning is a subset of artificial intelligence that allows machines to learn
from data and make predictions or decisions based on that learning.
Q.Why Is Machine Learning Important ?
->Machine learning has become increasingly important in recent years due to
the vast amounts of data being generated and the need to extract meaningful
insights from that data.
It is being used in various industries such as healthcare, finance, retail,
transportation, and more.
3. TYPES OF MACHINE LEARNING
REINFORCEMENT
LEARNING
03
intelligent agent (computer program)
interacts with the environment and
learns to act within that.
UNSUPERVISED
LEARNING
02
a set of unlabelled data, which it is
required to analyze and find patterns
inside.
SUPERVISED
LEARNING
01
use of labeled datasets to train
algorithms that to classify data or
predict outcomes accurately.
4. Q.What are benefits and costs of MACHINE LEARNING?
BENEFITS:-
i.Improved Efficiency: Machine learning can
help automate processes and tasks, reducing the
time and effort required to complete them.
ii.Better Decision-Making: Machine learning
can analyze large datasets and provide insights
that can inform decision-making and improve
accuracy.
iii.Personalization: Machine learning can help
personalize experiences for users, such as
personalized product recommendations, by
analyzing their behavior and preferences.
iv.Prediction: Machine learning can make
accurate predictions based on patterns and
trends in data, which can help organizations
make more informed decisions
COSTS:-
i.Data Requirements: Machine learning algorithms
require large amounts of data to be trained effectively,
which can be costly to obtain and process.
ii.Expertise: Developing and implementing machine
learning models requires specialized knowledge and
expertise, which can be expensive to acquire and
maintain.
iii.Computational Power: Machine learning models
require significant computational power, which can be
expensive to maintain and scale as the size of the data
increases.
iv.Bias and Fairness: Machine learning models may
reflect biases in the data they are trained on, leading to
unfair or discriminatory outcomes.
5. Future of MACHINE LEARNING
The future of machine learning is expected to be very exciting and promising. Here are some trends that are likely to shape the future
of machine learning:
Advancements in Deep Learning: Deep learning is a subset of machine learning that involves training neural networks with large
amounts of data. As more data becomes available, we can expect deep learning algorithms to become more accurate and
sophisticated.
More Applications of Machine Learning: Machine learning is already being used in many fields such as healthcare, finance, and
manufacturing. In the future, we can expect more applications of machine learning in areas such as education, transportation, and
entertainment.
Increased Use of Reinforcement Learning: Reinforcement learning is a type of machine learning that involves training algorithms to
make decisions based on feedback from their environment. This technique is already being used in autonomous vehicles and
robotics, and we can expect it to be used in more applications in the future.
More Focus on Explainability: As machine learning becomes more pervasive, there will be increased focus on making the algorithms
explainable. This will enable us to understand how the algorithms make decisions and identify potential biases.
Greater Collaboration between Humans and Machines: In the future, we can expect to see more collaboration between humans and
machines. This will involve machines taking on more mundane and repetitive tasks, freeing up humans to focus on more creative and
strategic tasks.
Overall, the future of machine learning is very bright and we can expect to see many exciting developments in the years to come.
6. ENHANCEMENT OF MACHINE LEARNING
❏ Reframe the problem
❏ Provide more data samples
❏ Add context to the data
❏ Use meaningful data and features
❏ Cross-validation
❏ Hyperparameter tuning
❏ Choose a different algorithm