Difference between Artificial Intelligence, Machine Learning, Deep Learning and Active Learning

ARTIFICIAL INTELLIGENCE
PhD Sch: Sanjay Srivastava
B.Arch. CeCP. MUDP. CePPM. AIIA. FISLE. FIBE
Guide: Prof Dr Alok Sharma

Difference between AI, Ml, DL & AL 2
Difference Between
Artificial Intelligence, Machine learning,
Deep Learning & Active Learning.

Artificial Intelligence AI
• AI refers to the concept of machines
mimicking human cognition. To reference
artificial intelligence is to allude to machines
performing tasks that only seemed plausible
with human thinking and logic.
• In the real world today, one of the most
ubiquitous forms of AI might manifest
themselves in the form of conversational AI.
Conversation AI may include multimodal
inputs (e.g. voice, facial recognition) with
multimodal outputs (e.g image, synthesized
voice). All of these modalities & their
integration can be considered part of AI.

Modulations relevant to Urban Planning
decision making .
• Urban planning, is a multi-layer exercise, that is to say
one looks at the urban area, initially, with reference and
focus on just one aspect of the city at a time ..out of say:
• 1. Population growth,
• 2. Physical spread of town that is land area , nature of land used it's
topography it's natural drainage initial and final states etc.
• 3.Traffic routes traffic modes public preference , cost sustain various traffic
options now & in future,
• 4. Spread of amenities like hospitals , playgrounds, schools and community
centres, large assembly spaces and
• 5. Distribution of utilities , water electricity
• 6. Removal of waste water and garbage management etc.
• Besides more recent concerns like ……

Modulations relevant to Urban
Planning decision making .
• 7. Time spent productively at work or home vs wasted in transport
• 8. Mental health of residents, physical health spread of disease etc.
• 9. Carbon footprint of the city
• 10. Ecological concerns and goals
• 11. Aspirations of people for the city
• 12. It's position and potential in the region and administrative
hierarchy.
• And Subsequently, we look at ALL the layers
superimposing one over the other and iterate the impact
of one over the other .

Superimpose, Extrapolate &
Evaluate the layers
• After mapping, quantifying and
extrapolating the growth/decline in
each of these layers is over, the
Planner steps in to evaluate and create
a plan which perhaps synthesises all
aspects in a balanced proposition.
• In AI. the planner defines & system
solves for the defined boundary
conditions then, planner re-evaluates
the complete picture

Supervised Learning
• These exercises continue, within a supervised
learning environment. The planners intervention is
driven and quantified by public policy, declared
goals and objectives.
• Iteration are done for costs, recurrent maintenance
costs, Total lifetime costs, serviceability issues,
Recouped investments , public benefit are
incorporated as boundary conditions and
algorithms iterate repeatedly for best case
scenarios.

Algorithms & Machine Learning
• In the next stage Algorithms define the
results and outcomes of all aspects of
the plan, which in turn lead to more
robust and complete scenarios with
well defined stresses on each linkage.
• Machine learning, deep learning, and
active learning are approaches used to
implement total AI environments.

Algorithms & Machine Learning
• Hence we see the cyclical
nature of maths,
scenarios, iterations,
algorithms, human
intervention and
machine learning leading
back to iterations till a
final solution meeting
objectives of public
policy is achieved !

Comparitive Definition AI ~ML
• If AI is when a computer can carry out a
set of tasks based on instruction, ML is a
machine’s ability to ingest, parse, and
learn from that data itself in order to
become more accurate or precise about
accomplishing that task.
• While other statistical methods for
learning exist, through recent ML
advancements, practitioners have revived
the concept of neural networks, which are
a series of algorithms that act—as one
might assume—like the human brain.

Deep Learning, Weights, &
Neural Network Activity
• As machine learning has advanced,
researchers and programmers have dived
deeper into what algorithms are able to
accomplish.
• A layer beyond machine learning, we find
deep learning. There are a few, similar
definitions for deep learning.
• The simplest definition for deep learning is
that it is “a set of algorithms in machine
learning that attempt to learn in multiple
levels,” where the lower-level concepts help
define different higher-level concepts.

• Within a neural network, each processor
or “neuron,” is typically activated through
sensing something about its
environment, from a previously activated
neuron, or by triggering an event to
impact its environment. The goal of
these activations is to make the
network—which is a group of ML
algorithms—achieve a certain outcome.
Deep learning is about “accurately
assigning credit across many such stages”
of activation.

• Within a neural network, each processor
or “neuron,” is typically activated through
sensing something about its environment,
from a previously activated neuron, or by
triggering an event to impact its
environment. The goal of these activations
is to make the network—which is a group
of ML algorithms—achieve a certain
outcome. Deep learning is about
“accurately assigning credit across many
such stages” of activation.

Active Learning
Chooses Its Own Data
• Most ML algorithms require annotated text,
images, speech, audio or video data.
• But, with the right resources and right amount
of data, practitioners can leverage ACTIVE
LEARNING.
• Active learning is the philosophy that “a
machine learning algorithm can achieve greater
accuracy with fewer training labels if it is
allowed to choose the data from which it
learns.” In order to choose the data from which
it learns, an active learning-based AI can query
humans in order to obtain more & better data.

Query strategy in Active learning
• Active learning in the real world is best
thought of as a method of training ML
algorithms.
• In practice, the idea behind active
learning is that data scientists can use
poorly trained AI to help identify—
through a Query Strategy, as outlined
previously—which pieces of data should
be used to train a better version of that
AI.

Differences Abound
Despite Inextricable Links
• While Deep learning is a more advanced
form of machine learning, which is used
to create artificial intelligence.
• Active learning leverages readily
available, and often imperfect, AI to
actively select new data that it believes
would be most beneficial when
developing the next, improved version
of the AI.

AI in Urban Planning
• Active Learning therefore can
significantly reduce the amount of data
required to develop a performant AI
system because it only learns from the
most relevant data.
• All of these terms are interconnected,
but each refers to a specific component
of creating AI. With the right
understanding of what each of these
phrases entail, we can get off on the
right foot creating our first step to AI
base in Urban Planning.

Difference between Artificial Intelligence, Machine Learning, Deep Learning and Active Learning

More Related Content

What's hot

Similar to Difference between Artificial Intelligence, Machine Learning, Deep Learning and Active Learning

Recently uploaded

In this document

Difference between Artificial Intelligence, Machine Learning, Deep Learning and Active Learning