Unblocking The Main Thread Solving ANRs and Frozen Frames
Artificial Intelligence & QA
1. QA
&
Created and Presented By
Maliha Ashraf
https://www.linkedin.com/in/maliha-ashraf
2. Agenda
Artificial Intelligence and Machine Learning Difference
Artificial Intelligence and its Types
QA Role in AI
Types of Machine Learning
Algorithms of Machine Learning
Linear Regression Example
3. What is Artificial Intelligence?
the term loosely applies to a range of
technologies that mirror human cognitive
functions
devices designed to act intelligently
the broader concept of machines being able
to carry out tasks in a way that we would
consider “smart”.
4. Then what is Machine Learning?
Machine learning is a type of artificial intelligence (AI) that allows
software applications to become more accurate in predicting outcomes
without being explicitly programmed.
It is the most common technique that powers AI
Often referred to as a subset of AI, it’s really more accurate to think of
it as the current state-of-the-art.
6. Types of Artificial Intelligence
1. Narrow AI:
This is AI at a specific field
For e.g. a text-based answering bot
More common
2. Generalized AI:
- Systems or devices which can, in theory, handle any task
- Less common
- Led to the development of Machine Learning
7. 1- Testing AI Software 2- AI in Software Testing
• Use AI to improve testing processes.
• Need to know AI techniques and their
implementation .
• Test the projects which use AI
• Should have an idea of testing these
projects
QA role in AI
8. 1- Testing AI Projects
1- Gather testing data
2- Determine Acceptance Criteria
3- Provide better feedback of QA efforts
9. 1- Testing AI Projects
1- Gather Testing Data:
System tested on more data, better
chances of determining the
performance accurately
10. 2- Acceptance Criteria
Determine what would be the acceptance criteria and evaluate
the application according to it.
For example: Often the intention of building an AI is for it to be
human-level or human-like in performance so the testing is
normally based on:
Does it have human level performance?
Does it seem like it is a human?
- Normally done using a Turing test.
1- Testing AI Projects
11. 3(a)- Statistical Terms
the acceptance criteria aren’t expressed in terms of
defect number, type, or severity. In fact, in most cases
they are expressed in terms of the statistical likelihood
of coming within a certain range.
Be prepared to support those assertions in statistical
terms
For example, be 95 percent confident that the
application will produce an answer within a given
range.
How can testers provide better feedback on their efforts on
such applications?
12. 3(b)- High-Level Understanding
Have a high-level understanding of the
underpinnings of the application, so that any
deficiencies might be able to be ascribed to a
particular application component.
How can testers provide better feedback on their efforts on
such applications?
13. 2- AI in Software Testing
Artificial intelligence (AI) algorithms learn from test assets to provide
intelligent insights like:
application stability
failure patterns
defect hotspots
failure prediction, etc.
These insights helps to anticipate, automate, and amplify decision-
making capabilities, thereby building quality early in the project lifecycle.
14. 2- AI in Software Testing
For this we need to know what are the techniques of artificial intelligence
The most common is machine learning
15. Types of Machine Learning
1. Supervised Learning
How it works:
This algorithm consist of a target / outcome variable (or dependent
variable) which is to be predicted from a given set of predictors
(independent variables). Using these set of variables, we generate a
function that map inputs to desired outputs. The training process
continues until the model achieves a desired level of accuracy on the
training data.
Examples of Supervised Learning:
Regression, Decision Tree etc.
16. Types of Machine Learning
2. Unsupervised Learning
How it works:
In this algorithm, we do not have any target or outcome variable to
predict / estimate. It is used for clustering population in different
groups, which is widely used for segmenting customers in
different groups for specific intervention.
Examples of Unsupervised Learning:
Apriori algorithm, K-means.
17. Types of Machine Learning
3. Reinforcement Learning
How it works:
Using this algorithm, the machine is trained to make specific
decisions. It works this way: the machine is exposed to an
environment where it trains itself continually using trial and error.
This machine learns from past experience and tries to capture the
best possible knowledge to make accurate business decisions.
Examples of Reinforcement Learning:
Markov Decision Process
18. Common Machine Learning Algorithms
These algorithms can be applied to almost any data problem:
Linear Regression
Logistic Regression
Decision Tree
SVM
Naive Bayes
KNN
K-Means
Random Forest
19. Linear Regression
Supervised learning Algorithm
It is used to estimate real values (cost of houses, number of calls, total
sales etc.) based on continuous variable(s).
How it works:
We establish relationship between independent and dependent
variables by fitting a best line.
This best fit line is known as regression line and represented by a linear
equation Y= a *X + b.