Scribd
Upload
148 views21 pages

Data Representation in ML

1. TensorFlow is an open source machine learning framework developed by Google. It is commonly used for computer vision and natural language processing tasks. 2. PyTorch is a Python-based deep learning framework developed by Facebook. It is popular for computer vision, NLP, and recommender systems. 3. Keras is a high-level neural network API that runs on top of TensorFlow or Theano. It is easy to use and good for rapid prototyping of deep learning models. Some common deep learning applications include computer vision (image recognition, object detection), natural language processing (machine translation, text generation), speech recognition, recommender systems

Uploaded by

Amrin Mulani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
148 views21 pages

Data Representation in ML

1. TensorFlow is an open source machine learning framework developed by Google. It is commonly used for computer vision and natural language processing tasks. 2. PyTorch is a Python-based deep learning framework developed by Facebook. It is popular for computer vision, NLP, and recommender systems. 3. Keras is a high-level neural network API that runs on top of TensorFlow or Theano. It is easy to use and good for rapid prototyping of deep learning models. Some common deep learning applications include computer vision (image recognition, object detection), natural language processing (machine translation, text generation), speech recognition, recommender systems

Uploaded by

Amrin Mulani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

MAchine Learning

What is machine Learning


• Machine learning is an application of artificial intelligence (AI) that
provides systems the ability to automatically learn and improve from
experience without being explicitly programmed.
• Machine learning focuses on the development of computer
programs that can access data and use it to learn for themselves.
• The primary aim is to allow the computers learn
automatically without human intervention or assistance and adjust
actions accordingly.
When to use Machine Learning

1.They involve a repeated decision or evaluation which you want


to automate and need consistent results.
2.It is difficult or impossible to explicitly describe the solution or
criteria behind a decision.
3.You have labeled data, or existing examples where you can
describe the situation and map it to the correct result.
Deep Learning

subset of Machine Learning

Deep learning algorithms attempt to draw


similar conclusions as humans would by
continually analyzing data with a given
logical structure.
Types of Data used in Deep Learning
• Sound (Voice Recognition)
• Text (Classifying Reviews)
• Images (Computer Vision)
• Time Series (Sensor Data,
Web Activity)
• Video (Motion Detection)
Data Attributes
• Relevancy
• Proper Classification
• Formatting
• Accessibility
Examples
• Classification: This image represents a horse; this email looks like
spam; this transaction is fraudulent
• Clustering: These two sounds are similar. This document is probably
what user X is looking for
• Predictions: Given their web log activity, Customer A looks like they
are going to stop using your service
Limitations and challenges

• requires large amounts of data


• cannot handle multitasking
• long-term planning is difficult
1.Healthcare: Machine Learning is widely used in the
healthcare industry. It helps healthcare researchers to analyze
data points and suggest outcomes. Natural language processing
helped to give accurate insights for better results of patients.
Further, machine learning has improved the treatment methods
by analyzing external data on patients' conditions in terms of X-
ray, Ultrasound, CT-scan, etc. NLP, medical imaging, and
genetic information are key areas of machine learning that
improve the diagnosis, detection, and prediction system in the
healthcare sector.

2.Automation: This is one of the significant applications of


machine learning that helps to make the system automated. It
helps machines to perform repetitive tasks without human
intervention. As a machine learning engineer and data scientist,
you have the responsibilities to solve any given task multiple
times with no errors. However, this is not practically possible
for humans. Hence machine learning has developed various
models to automate the process, having the capability of
performing iterative tasks in lesser time.
3.Banking and Finance: Machine Learning is a subset of AI
that uses statistical models to make accurate predictions. In the
banking and finance sector, machine learning helped in many
ways, such as fraud detection, portfolio management, risk
management, chatbots, document analysis, high-frequency
trading, mortgage underwriting, AML detection, anomaly
detection, risk credit score detection, KYC processing, etc.
Hence, machine learning is widely applied in the banking and
finance sector to reduce error as well as time.
4. Transportation and Traffic Prediction: This is one of the most
common applications of Machine Learning that is widely used by all
individuals in their daily routine. It helps to ensure highly secured
routes, generate accurate ETAs, predict vehicle breakdown, Driving
Prescriptive Analytics, etc. Although machine learning has solved
transportation problems, it still requires more improvement.
Statistical machine learning algorithms helps to build a smart
transportation system. Further, deep Learning explored the complex
interactions of roads, highways, traffic, environmental elements,
crashes, etc. Hence, machine learning technology has improved daily
traffic management as well as a collection of traffic data to predict
insights of routes and traffic.
Applications of Deep Learning

Text generation
Customer experience Aerospace and military

Computer vision Industrial automation

Medical research
Adding color
Classification of Machine Learning Models:

Unsupervised Learning
Supervised Learning
•Clustering
•Classification
•Association Rule
•Regression
•Dimensionality Reduction
How to choose the right machine learning model
The process of choosing the right machine learning model to solve a problem can be time
consuming if not approached strategically.
Step 1: Align the problem with potential data inputs that should be considered for the
solution. This step requires help from data scientists and experts who have a deep
understanding of the problem.

Step 2: Collect data, format it and label the data if necessary. This step is typically led by
data scientists, with help from data wranglers.

Step 3: Chose which algorithm(s) to use and test to see how well they perform. This step
is usually carried out by data scientists.

Step 4: Continue to fine tune outputs until they reach an acceptable level of accuracy.
This step is usually carried out by data scientists with feedback from experts who have a
deep understanding of the problem.
Case Study
• Being a researcher you are required to investigate whether a person
has H1N1 or not.
• What kind of data you would need?
• how would you collect data?
• What would be your hypothesis statement?
• How would you analyze data and what aspect you are looking for?
• What kind of graphs you would look at?
Quick Activity

• Open Source Deep Learning Tools


• Commonly-Used Deep Learning Applications

You might also like