Scribd
Upload
23 views

Deep Learning Part 2

The document provides examples of machine learning applications and discusses different types of machine learning: - Applications include detecting tumors, forecasting revenue, detecting fraud, classifying news, flagging offensive comments, summarizing documents, creating chatbots, and recommending products. - The three main types are supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses labeled training data to learn input-output mappings, unsupervised learning finds patterns in unlabeled data, and reinforcement learning involves an agent learning policies through trial-and-error interactions with an environment.

Uploaded by

statistikatiusd
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
23 views

Deep Learning Part 2

The document provides examples of machine learning applications and discusses different types of machine learning: - Applications include detecting tumors, forecasting revenue, detecting fraud, classifying news, flagging offensive comments, summarizing documents, creating chatbots, and recommending products. - The three main types are supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses labeled training data to learn input-output mappings, unsupervised learning finds patterns in unlabeled data, and reinforcement learning involves an agent learning policies through trial-and-error interactions with an environment.

Uploaded by

statistikatiusd
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

• Examples of Applications

Detecting tumors in brain scans.


• Forecasting a company’s revenue next year based on many
performance metrics
• Detecting credit card fraud
• Automatically classifying news articles
• Automatically flagging offensive comments on discussion
forums
• Summarizing long documents automatically
• Examples of Applications
Creating a chatbot or a personal assistant
• Making an app react to voice commands
• Segmenting clients based on their purchases so that you can
design a different marketing strategy for each segment
• Examples of Applications
Representing a complex, high-dimensional dataset in a clear
and insightful diagram
• Recommending a product that a client may be interested in,
based on past purchases
• Building an intelligent bot for game
• Types of Machine Learning
According to the amount and type of supervision they get
during training
• Supervised Learning:
• used most in real-world applications,
• most rapid advancements and innovation
• Unsupervised Learning
• the most widely used form of machine
learning after supervised learning
• Reinforcement Learning
Supervised Learning
• Supervised learning refers to algorithms that
learn x to y or input to output mappings
• The key characteristic of supervised learning is
that you give your learning algorithm examples
to learn from, including the right answers
(correct label y for a given input x).
Supervised Learning
• By seeing correct pairs of input x and desired
output label y that the learning algorithm
eventually learns to take just the input alone
without the output label and gives a
reasonably accurate prediction or guess of the
output.
Supervised Learning
• If the input x is an email and the output y is this
email, spam or not spam, this gives you your
spam filter.
Supervised Learning
• Classification problem: we're trying to predict
only a small number of possible outputs or
categories.
Supervised Learning
• Regression problem: we're trying to predict a
number from infinitely many possible numbers
• Unsupervised learning
In unsupervised learning, the training data is unlabeled. The
system tries to learn without a teacher to find some structure
or some pattern or just find something interesting in the data.
• We call it unsupervised because we’re not trying to supervise
the algorithm.
• A typical problem in unsupervised learning is clustering,
anomaly detection and dimension reduction.
Unsupervised learning
(clustering)
Unsupervised learning
• Anomaly detection
(anomaly detection)
is used to detect unusual events.
This turns out to be really important for fraud
detection in the financial system, where unusual
events, unusual transactions could be signs of fraud
and for many other applications.
Unsupervised learning
• The dimensionality
(dimensionality
reduction reduction)
lets you take a big data-
set and almost magically compress it to a much
smaller data-set while losing as little information as
possible.
•
Reinforcement Learning
The learning system, called an agent in this context, can
observe the environment, select and perform actions, and get
rewards in return (or penalties in the form of negative
rewards).
• It must then learn by itself what is the best strategy, called a
policy, to get the most reward over time.
• A policy defines what action the agent should choose when it
is in a given situation.
• It is not very widely applied in commercial applications yet
today, but it is one of the pillars of machine learning and has
lots of exciting research backing it up and improving it every
single day.
Reinforcement Learning
Course Contents

• Perceptron and Multi-layer Perceptrons


• Regression
• Classification
• Convolutional Neural Networks (CNN)
• Computer vision
• Long Short Term Memory (LSTM)
• Time series

You might also like