Scribd
Upload
27 views41 pages

2 - 2AIops-Foundations

Uploaded by

ranamzeeshan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
27 views41 pages

2 - 2AIops-Foundations

Uploaded by

ranamzeeshan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 41

AIops – Artificial Intelligence Operations

AI
Foundations:
AI Foundations refer to the
fundamental concepts and
principles that form the basis of
Artificial Intelligence (AI) as a field
of study and practice.
These foundations provide the
building blocks upon which more
advanced AI techniques and
applications are developed.
AIOps Keys Foundations

Algorithm & Ethics &


Probability &
Computational Responsible AI
Machine Learning Statistics
Methods

Data & Data Knowledge & Congnitive


Analytics Representation Computing
Foundation 1 – Machine Learning

MACHINE LEARNING IS A SUBSET OF AI THAT THIS INCLUDES TECHNIQUES SUCH AS SUPERVISED


INVOLVES TRAINING ALGORITHMS TO LEARN FROM LEARNING, UNSUPERVISED LEARNING,
DATA REINFORCEMENT LEARNING, AND DEEP LEARNING.
I can learn everything with my past Experience

I can learn by using past data with machine


learning
OUTPUT

Hey! It is a
What is it?
ball
010010
101010
Environment
Reward Best Action

Model Trained

Selection of
INPUT RAW State Algorithm
DATA
Agent
INPUT

Model Training
Machine
Learning

Supervised unsupervised Reinforcement

Task Driven Data Driven Learn from


(Predict next value) (Identity Clusters) Mistakes
AIOps Keys Foundations

Algorithm & Ethics &


Probability &
Computational Responsible AI
Machine Learning Statistics
Methods

Data & Data Knowledge & Congnitive


Analytics Representation Computing
Foundation 2 -
Data and Data
Analytics
Data is a critical component of AI,
as it provides the raw material for
training and testing AI algorithms.
Data analytics techniques, such as
data preprocessing, feature
engineering, and data
visualization, are used to analyze
and transform data into a format
that can be used for machine
learning and other AI tasks.
AIOps Keys Foundations

Algorithm & Ethics &


Probability &
Computational Responsible AI
Machine Learning Statistics
Methods

Data & Data Knowledge & Congnitive


Analytics Representation Computing
Foundation 3 - Probability and Statistics:

Probability and statistics are foundational


concepts in AI, as they are used to model
and quantify uncertainty in data and make
probabilistic predictions.

Techniques such as Bayesian inference,


statistical hypothesis testing, and
probability distributions are commonly
used in AI applications.
A statistical hypothesis is an assumption made by the researcher about the data of the population collected for any
experiment. It is not mandatory for this assumption to be true every time. Hypothesis testing, in a way, is a formal
process of validating the hypothesis made by the researcher.
Probability
Distrubtion:
• In probability
theory and statistics,
a probability distribution is the
mathematical function that gives
the probabilities of occurrence of
different possible outcomes for
an experiment.[1][2] It is a
mathematical description of
a random phenomenon in terms
of its sample space and
the probabilities of events (subs
ets of the sample space).[3]
AIOps Keys Foundations

Algorithm & Ethics &


Probability &
Computational Responsible AI
Machine Learning Statistics
Methods

Data & Data Knowledge & Congnitive


Analytics Representation Computing
AI involves the use of various
algorithms and computational
methods for solving complex
problems. These include algorithms
for search and optimization,
pattern recognition, clustering,
classification, and regression,
Foundation 4 - among others. Efficient
implementation and optimization
Algorithms and of these algorithms are crucial for
Computational AI system performance.

Methods
Search Algorithm:
Optimization Algorithm
• Optimization involves identifying and analyzing
different options, evaluating their pros and cons, and
selecting the one that provides the optimal result
according to a specific criteria or objective function. The
goal of optimization is often to maximize or minimize a
particular objective, such as maximizing profits,
Pattern Recognization:
Example of Pattern Recognition:
Classification:
Regression
Clustering
AIOps Keys Foundations

Algorithm & Ethics &


Probability &
Computational Responsible AI
Machine Learning Statistics
Methods

Data & Data Knowledge & Congnitive


Analytics Representation Computing
Foundation 5 - Knowledge Representation and Reasoning

Knowledge representation and reasoning are central to AI systems


that can understand and reason about complex information.

Techniques such as logic, semantic networks, and ontologies are used


to represent and manipulate knowledge for reasoning and decision-
making.
Knowledge Representation Techniques:
• Semantic networks are alternative of predicate logic
for knowledge representation. In Semantic networks, we
can represent our knowledge in the form of graphical
networks. This network consists of nodes representing
objects and arcs which describe the relationship
between those objects.
• In a frame, each concept is represented as a node or
entity, and the relationships between the concepts are
represented as links or edges. The frame structure
provides a way to organize and represent knowledge in a
way that is easy to understand and process for both
humans and machines.
•
AIOps Keys Foundations

Algorithm & Ethics &


Probability &
Computational Responsible AI
Machine Learning Statistics
Methods

Data & Data Knowledge & Congnitive


Analytics Representation Computing
Foundation 6 -
Cognitive
Computing
Cognitive computing involves the
study of human cognition and the
development of AI systems that can
emulate human cognitive abilities,
such as perception, language
processing, and reasoning.
Understanding human cognition is
essential for developing AI systems
that can interact with humans in
natural and intuitive ways.
AIOps Keys Foundations

Algorithm & Ethics &


Probability &
Computational Responsible AI
Machine Learning Statistics
Methods

Data & Data Knowledge & Congnitive


Analytics Representation Computing
Ethics and responsible AI considerations are increasingly recognized as
critical foundations of AI.
These include ethical considerations such as fairness, transparency,
accountability, and bias mitigation, as well as responsible AI practices
that ensure AI is developed and deployed in a manner that aligns with
human values, societal well-being, and legal requirements.
Understanding and applying these AI foundations is crucial for
practitioners and researchers in the field of AI to develop robust,
effective, and ethical AI systems.
These foundations provide the theoretical underpinnings and practical
tools necessary for advancing the field of AI and developing innovative
AI applications.
We have learnt about Key take aways such as:

• Machine Learning
• Data & Data analytics
• Probability & statistics
• Knowledge & Representation
• Algorithm & Computational Methods
• Cognitive Computing
• Ethics & Responsible AI

KEY TAKEAWAYS:
Thank you.
Take a short break before starting
the next session

You might also like