Jimena Alegria

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 15

Introduction to Machine learning

Jimena Alegria
Machine learning is a subfield Machine learning is behind
of artificial intelligence that chatbots and predictive text,
uses algorithms trained on language translation apps, the
data sets to create models shows Netflix suggests to you,
that enable machines to and how your social media
perform tasks that would feeds are presented. It powers
otherwise only be possible for
autonomous vehicles and
humans, such as categorizing
machines that can diagnose
images, analyzing data, or
medical conditions based on
predicting price fluctuations.
images.
what is machine learning?
Machine Learning
Machine learning is the
Examples
process of a computer
Ranking posts on social
modeling human intelligence, media
and autonomously improving Searching for the best
over time. Machines are able answers to questions
to make predictions about Enabling business
the future based on what intelligence
they have observed and
learned in the past.
Why Machine Learning Matters
See trends in customer behavior and business
operational patterns
Support the development of new products
Extract better quality information
Increase productivity and speed in processes
Reduce costs
Extract more value from data
Help businesses in decision-making
Types of Machine Learning Supervised learning is the machine
Machine learning involves learning task of learning a function that
maps an input to an output based on
showing a large volume of
example input-output pairs.
data to a machine so that it
can learn and make unsupervised learning is the machine
learning task of learning a function that
predictions, find patterns, or
maps an input to an output based on
classify data. The three example input-output pairs.
machine learning types are
Reinforcement learning (RL) is a type
supervised, unsupervised,
of machine learning that involves
and reinforcement learning. learning how to make a sequence of
decisions.
Supervised Learning
Supervised learning is a
paradigm in machine learning
where input objects and a
desired output value train a
model. The training data is
processed, building a function
that maps new data on
expected output values.
Unsupervised Learning
Unsupervised learning is a
kind of machine learning
where a model must look for
patterns in a dataset with no
labels and with minimal
human supervision. This is in
contrast to supervised
learning techniques, such as
classification or regression,
where a model is given a
training set of inputs and a
set of observations, and must
learn a mapping from the
inputs to the observations.
Reinforcement Learning
Reinforcement Learning
(RL) is the science of
decision making. It is
about learning the
optimal behavior in an
environment to obtain
maximum reward.
How Machine Learning Works

Machine learning is a subfield of artificial


intelligence, which is broadly defined as the
capability of a machine to imitate intelligent human
behavior. Artificial intelligence systems are used to
perform complex tasks in a way that is similar to
how humans solve problems.
Training a Machine Learning Model
Build a foundation of statistics, programming, and a bit of math.
Immerse yourself in the essential theory behind ML.
Use ML packages to practice the 9 essential topics.
Adjust your mindset and believe you can practice and apply machine
learning.
Use a systemic process to work through problems.
Choose a programming language for ML development, such as Python or
R.
Familiarize yourself with the basics of the chosen programming language
and its libraries for data analysis and visualization.
Model Evaluation

Accuracy shows how often a classification ML


model is correct overall. Precision shows how often
an ML model is correct when predicting the target
class. Recall shows whether an ML model can find
all objects of the target class. Consider the class
balance and costs of different errors when
choosing the suitable metric.
Challenges in Machine Learning
1. Poor Quality of Data 2. Underfitting of Training Data 3. Overfitting of Training Data
Data plays a significant role in This process occurs when data is Overfitting refers to a machine
the machine learning process. unable to establish an accurate learning model trained with a
One of the significant issues relationship between input and massive amount of data that
that machine learning output variables. negatively affect its
professionals face is the performance. It is like trying to
absence of good quality data. fit in Oversized jeans.

4. Machine Learning is a 5. Lack of Training Data 6. Slow Implementation


Complex Process The most important task you This is one of the common
The machine learning need to do in the machine issues faced by machine
learning professionals. The
industry is young and is learning process is to train the
machine learning models are
continuously changing. data to achieve an accurate
highly efficient in providing
Rapid hit and trial output. Less amount training accurate results, but it takes
experiments are being data will produce inaccurate or a tremendous amount of
carried on. too biased predictions. time.
Future of Machine Learning
Increased adoption of AI
Use of explainable AI
Enhanced natural language processing
Edge computing
Quantum computing can boost machine learning
capabilities
AutoML will facilitate the end-to-end model development
process
Machine learning will revolutionize processes, enhance
decision-making, and uncover valuable insights from vast
data.
Machine Learning in Your Daily Life
Virtual personal assistants like Siri, Alexa, and Google Now
Traffic predictions
Video surveillance
Social media services
Email spam and malware filtering
Online customer support
Search engine result refining
Product recommendations
How has Machine Learning Affected FinTech
Machine learning has had a significant impact
on the fintech industry, enabling financial
institutions to improve efficiency, reduce costs,
and offer personalized products and services.
Machine learning algorithms have also
improved fraud detection and risk management
in the financial industry, saving institutions
billions of dollars every year.

You might also like