Artificial Intelligence Buzzwords and related topics.pptx
1. ABC to AI and Its Buzzwords
Dr. Noman Hossain, PhD
Assistant Professor, Dept. of CSE, ULAB
Date: 31 Oct, 2023
Venu: Department of ICT
Delivered
to
Training on the use of AI-Driven Data Analytics
2. Definitions of AI
• AI- Artificial Intelligence; actually it means highly
processed valuable information (intelligence – which
forms knowledge) and formally, human like traits of
machines/devices/ software (digital twin) those actually
possessed by human or any natural beings.
3. Definitions of AI
• AI- Artificial Intelligence; actually it means highly
processed valuable information (intelligence – which
forms knowledge) and formally, human like traits of
machines/devices/ software (digital twin) those actually
possessed by human or any natural beings.
4. Definitions of AI
• AI- Artificial intelligence (AI) is a set of technologies
that enable computers to perform a variety of advanced
functions, including the ability to see, understand and
translate spoken and written language, analyze data,
make recommendations, and more.
• For example, optical character recognition (OCR) uses
AI to extract text and data from images and documents,
turns unstructured content into business-ready structured
data, and unlocks valuable insights.
5. Definitions of AI
• Artificial intelligence is a field of science concerned
with building computers and machines that can reason,
learn, and act in such a way that would normally require
human intelligence or that involves data whose scale
exceeds what humans can analyze.
• AI is a broad field that encompasses many different
disciplines, including computer science, statistics, hardware
and software engineering, linguistics, neuroscience, and even
philosophy and psychology.
6. Definitions of AI
• On an operational point of view, AI is a set of
technologies that are based primarily on machine
learning and deep learning, used for data analytics,
predictions and forecasting, object categorization,
natural language processing, recommendations,
intelligent data retrieval, and more.
.
7. Actual Meaning of AI
• On the scientific point of view, AI is nothing but formulizing
raw date into various mathematical and statistical formulation
to save parameters of different keypoints of interest.
• We can write y=mx+c for the data give in the chart. The
related parameters can be derived from the data also.
• Once we complete the model, related parameters will be saved into a
serializable file.
9. How AI Forms ???
AI forms from the raw data accumulated over times.
We will further observe that, AI is nothing but super processed
information organized in mathematical formula.
10. Type of AI
1. Reactive machines: limited AI that only reacts to different
kinds of stimuli based on preprogrammed rules. Does not use
memory and thus cannot learn with new data. IBM’s Deep
Blue is an example of a reactive machine.
2. Limited memory: Most modern AI is considered to be
limited memory. It can use memory to improve over time by
being trained with new data, typically through an artificial
neural network or other training model. Deep learning, a
subset of machine learning, is considered limited memory
artificial intelligence.
11. Type of AI
3. Theory of mind: Theory of mind AI does not currently exist,
but research is ongoing into its possibilities. It describes AI
that can emulate the human mind and has decision-making
capabilities equal to that of a human.
4. Self aware: A step above theory of mind AI, self-aware AI
describes a mythical machine that is aware of its own
existence and has the intellectual and emotional capabilities
of a human. Like theory of mind AI, self-aware AI does not
currently exist.
18. Steps of Data Modeling
1. Get the candidate system data for study
2. Select a modeling approach
3. Apply your methodology
4. Solve it and Get result(model)
5. Deploy (model)
6. Done!
23. Ways of Training Data
ML
DL
RL
Raw
Data Dataset >>
>>
>> Model (intelligence/ knowledge
base)
training
learning
1.Supervised learning
2.Unsupervised
learning
3.Reinforcement
learning
Notes:
Training: Humans Point of
view
24. Ways of Training Data
1.Supervised learning: It is a way of machine learning that maps a
specific input to an output using labeled training data (structured
data).
2.Unsupervised learning: It is a way of machine learning model that
learns patterns based on unlabeled data (unstructured data). Unlike
supervised learning, the end result is not known ahead of time. Rather,
the algorithm learns from the data, categorizing it into groups based
on attributes.
3.Reinforcement learning: It is a way of machine learning model that
can be broadly described as “learn by doing.” An “agent” learns to
perform a defined task by trial and error (a feedback loop) until its
performance is within a desirable range. The agent receives positive
and negative reinforcement based on feedback of current performance.
32. DECISION
TREE ALGORITHMS
•Classification and Regression Tree (CART)
•Iterative Dichotomiser 3 (ID3)
•C4.5 and C5.0 (different versions of a powerful
approach)
•Chi-squared Automatic Interaction Detection
(CHAID)
•Decision Stump
•M5
•Conditional Decision Trees
44. We programmed this
robot to draw the
sketch of HE President
Xi Jinping
MicroClo
My Endeavor Towards AI & Robotics
45. I used to program
different embedded
system to avail
intelligence. Some of
the patents in this
domain awarded in
Chinese national
competition in 2017.
MicroClo
My Endeavor Towards AI & Robotics
46. I used to program
different embedded
system to avail
intelligence. Some of
the patents in this
domain awarded in
Chinese national
competition in 2017.
MicroClo
My Endeavor Towards AI & Robotics
