Artificial Intelligence and Machine Learning

Artificial intelligence (AI) refers to simulating human intelligence through machine learning algorithms that enable systems to perform tasks like problem solving, perception, reasoning and learning. Machine learning is a key part of AI that allows systems to learn from data and improve over time, with the two main types being supervised learning using labeled data and unsupervised learning using unlabeled data.

Uploaded by

Parcellover Syazirahfah

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

0% found this document useful (0 votes)

22 views

Artificial Intelligence and Machine Learning

Uploaded by

Parcellover Syazirahfah

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/ 2

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are

programmed to think and act like humans. AI involves the development of algorithms that can
perform various cognitive tasks, such as learning, perception, reasoning and problem solving.

Machine learning is a key component of AI that enables machines to learn from data and improves
their performance over time. There are two main types of machine learning: supervised learning and
unsupervised learning. In supervised learning, machines are trained on labeled data, while in
unsupervised learning, machines learn from unlabeled data.

What AI Business idea?

 Automatic Quality Control – A computer vision system could be used to automate quality
control processes in various manufacturing industries. The system could analyze product
images or videos to detect any defects or anomalies and reject any defective products.
 Retail Analytics – A computer vision system could be sed to analyze customer behavior in
retail stores. The system could track customer movements, determine which items they are
interested in, and provide recommendations based on their preferences. It could also be
used to optimize store layouts and improve inventory management.
 Security surveillance – A computer vision system could be used to monitor and analyze
surveillance footage in public spaces or commercial properties. The system could identify
suspicious behavior –

Real problem and how to solved

Problem: Solves the Bank forged signature

Solution: there are several existing technological solutions that banks can implement to enhanced
their security measures. Some examples may include:

- Biometrics authentication, such as fingerprint scanning or facial recognition, as well as digital

signatures that are encrypted and difficult to forge.

Another solution to help banks with problem related to forgery is to develop a computer vision-
based system that can identify and verify the authenticity of signatures in real-time using machine
learning algorithms:

1. Collect a large dataset of signature images,

2. Preprocess the images by resizing, cropping, and normalizing the signatures,
3. Train a deep learning model (such as convolutional neural network) on preprocessed
signature images to distinguish between genuine and forged signatures,
4. Deploy the model to a software platform into the bank’s existence security system to identify
any forged signatures and alert the bank staff in real-time.

This solution would not only help the bank streamlines its signature verification process but
could also potentially save a lot of time and money by avoiding the need for manual checks.
Additionally, building this system could open up opportunities for future collaborations with
other industries that could benefits from signature verification technology.
The accuracy that it needs to pass for the beta test?

Accuracy it needs to pass the beta test will depend on a number of factors, including what
industry they’re working in and specific use case for the signature verification system.
Generally speaking, higher accuracy levels are preferred because they reduce the likelihood
of false positives or false negatives, which can lead to incorrect results.

However, there is no set threshold for what constitutes a “good” accuracy level for a beta
test. The best approach is to aim for the highest possible accuracy while ensuring that the
development and testing process remains practical and feasible. You may also want to
consult with experts in the fields to get their input on what accuracy levels are realistic and
achievable for specific use case.

Ultimately, the goal of a beta test is to identify any potential issues or areas for
improvement, so even if the system doesn’t achieve the desired accuracy level during the
beta test, it still can help to improve the solution.

The Security?

Any computer system, including a signature verification system, can potentially be hacked.
That’s why