Scribd
Upload
10 views

How Supervised Learning Works

FDGHFDGH

Uploaded by

Thil Pa
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 views

How Supervised Learning Works

FDGHFDGH

Uploaded by

Thil Pa
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/ 4

How Supervised Learning Works:

1. Data Collection: Gather labeled data (input-output pairs)


2. Data Preprocessing: Clean, transform, and split data
3. Model Selection: Choose a suitable algorithm
4. Training: Train the model on labeled data
5. Testing: Evaluate the model on unseen data
6. Deployment: Use the trained model for predictions

Real-World Examples:

1. Image recognition (e.g., Facebook's facial recognition)


2. Speech-to-text systems (e.g., Siri, Google Assistant)
3. Product recommendation systems (e.g., Amazon, Netflix)

Medical diagnosis systems (e.g., IBM Watson Health

Key Performance Metrics:

1. Accuracy
2. Precision
3. Recall
4. F1-Score
5. Mean Squared Error (MSE)
6. Mean Absolute Error (MAE)

How Unsupervised Learning Works:

1. Data Collection: Gather unlabeled data


2. Data Preprocessing: Clean and transform data
3. Model Selection: Choose a suitable algorithm
4. Training: Train the model to identify patterns
5. Evaluation: Assess the quality of the discovered patterns

Real-World Examples:

1. Google News grouping similar news articles


2. Amazon's product recommendation system
3. Netflix's content suggestion algorithm
4. Image compression in digital cameras

Key Performance Metrics:

1. Silhouette Coefficient
2. Calinski-Harabasz Index
3. Davies-Bouldin Index
4. Precision-Recall Curve
5. Receiver Operating Characteristic (ROC) Curve
How Reinforcement Learning Works:

1. Initialization: Agent starts with random policy


2. Exploration: Agent takes actions, observes states/rewards
3. Learning: Agent updates policy based on rewards
4. Exploitation: Agent uses learned policy to maximize rewards

Real-World Examples:

1. Tesla's Autopilot system


2. Google's AlphaGo
3. Amazon's recommendation system
4. Video game AI (e.g., StarCraft)
5. Robotics control (e.g., Boston Dynamics)

Key Performance Metrics:

1. Cumulative Reward
2. Average Reward per Step
3. Episode Length
4. Success Rate
5. Regret

1.7 Explain the applications of machine learning towards real-life

Real-World Examples of Machine


Learning (ML)
. Facial recognition

People previously received name suggestions for their mobile photos and Facebook
tagging, but now someone is immediately tagged and verified by comparing and
analyzing patterns through facial contours.

And facial recognition paired with deep learning has become highly useful in
healthcare to help detect genetic diseases or track a patient’s use of medication
more accurately.

2. Product recommendations

Targeted marketing with retail uses machine learning to group customers based on
buying habits or demographic similarities, and by extrapolating what one person
may want from someone else’s purchases.

While some suggested purchase pairings are obvious, machine learning can get
accurate by finding hidden relationships in data and predicting what you want
before you know you want it

3. Email automation and spam filtering

Email automation is a direct result of successful machine learning, and one function
that goes most unnoticed is spam filtering.
Successful spam filtering adapts and finds patterns in email content that is
undesirable. This includes data from email domains, a sender’s physical location
message text and structure, and IP addresses.

It also requires help from users as they mark emails when they’re mistakenly filed.
With each marked email, a new data reference is added that helps with future
accuracy.

4. Financial accuracy

Abundant financial transactions that can’t be monitored by human eyes are easily
analyzed thanks to machine learning, which helps find fraudulent transactions.

One of the newest banking features is the ability to deposit a check straight from
your phone by using handwriting and image recognition to “read” checks and
convert them to digital text.

5. Social media optimization

Platforms from Facebook to Instagram and Twitter are using big data and artificial
intelligence to enhance their functionality and strengthen the user experience.

Machine learning has become helpful in fighting inappropriate content and cyber
bullying, which pose a risk to platforms in losing users and weakening brand loyalty.

6. Healthcare advancement

Healthcare brands such as Pfizer and Providence have begun to benefit from
analytics enhanced by human and artificial intelligence. There are some processes
that are better suited to leverage machine learning; machine learning integration
with radiology, cardiology, and pathology, for example, is leading to earlier
detection of abnormalities or heightened attention on concerning areas.

In the long run, machine learning will also benefit family practitioners or internists
when treating patients bedside because data trends will predict health risks like
heart disease.

As an example, wearables generate mass amounts of data on the wearer’s health


and many use AI and machine learning to alert them or their doctors of issues to
support preventative measures and respond to emergencies.

7. Mobile voice to text and predictive text

Machines are also capable of learning language in other formats. Like Siri and
Cortana, voice-to-text applications learn words and language then transcribe audio
into writing.

Predictive text also deals with language. Simple, supervised learning trains the
process to recognize and predict what common, contextual words or phrases will be
used based on what’s written.

Unsupervised learning goes further, adjusting predictions based on data. You may
start noticing that predictive text will recommend personalized words.

For instance, if you have a hobby with unique terminology that falls outside of a
dictionary, predictive text will learn and suggest them instead of standard words.
It’s working when autocorrect starts trying to predict them in normal conversation.
8. Predictive analytics

Predictive analytics is an area of advanced analytics that uses data to make


predictions about the future.

Techniques such as data mining, statistics, and modeling employ machine learning
and artificial intelligence to analyze current and historical data for any patterns or
anomalies that can help identify risks and opportunities, minimize the chance for
human errors, and increase speed and thoroughness of analysis.

With closer investigation of what happened and what could happen using data,
people and organizations are becoming more proactive and forward looking. Florida
International University is one example.

By integrating predictive models with data analysis from Tableau, they’re


communicating critical insights about academic performance before students are at
risk and supporting their individual needs to help them successfully complete all
courses and graduate.

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