Introduction to Artificial

Intelligence and the Road

Ahead
What is Artificial Intelligence (AI)

→ Definition: Artificial Intelligence (AI) is a branch of computer science that deals

with the development of computer systems that are capable of performing tasks
that normally require human intelligence.

→ Tasks: visual perception, speech recognition, decision-making, and language

translation.

→ Applications: AI techniques are used in many areas, including robotics, medical

diagnosis, marketing, self-driving cars, game playing, chatbots, etc.
History of AI

Copyright: Queensland Brain Institute - The University of Queensland

Traditional AI Approaches
Modern AI Approaches
→ Machine Learning: Algorithms that learn from data to make predictions or decisions without being
explicitly programmed for the task.

→ Deep Learning: Uses neural networks with many layers (deep networks) to learn from vast amounts of data,
often used in image and speech recognition.

→ Reinforcement Learning: A type of machine learning where an agent learns by interacting with
its environment to maximize cumulative reward, often used in robotics and game AI.

→ Generative AI: Algorithms that generate new data based on existing data, including techniques
like Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), used in
creating images, music, and text.
Need of AI

→ To improve the efficiency of processes, reduce costs, and make life easier for
people

→ To automate tedious tasks, improve decision-making, and provide more accurate

predictions

→ To mitigate the challenges posed by an ever-increasing human population (such as

resource scarcity, environmental degradation, and strained public services)
Weak AI Vs Strong AI Vs Super AI
Continued…
→ Strong AI, General AI, or Artificial General Intelligence (AGI):
→ refers to a type of artificial intelligence that can understand, learn, and perform any
intellectual task that a human being can do.
→ e.g. humanoids in Movies like Westworld(1973), Terminator3(2003), etc.

→ Weak AI, Narrow AI or specialized AI which is designed for specific tasks and has limited
ability to generalize its knowledge to other domains
→ E.g., Google search, Image recognition software, Siri, Alexa and other personal
assistants, Self-driving cars, IBM's Watson (is AI for business), Sofia(humanoid robot)

→ Super AI More intelligent than Humans

 Where Machine Learning Stands ?

The field of study interested in the

development of computer algorithms to
transform data into intelligent action is
known as machine learning.

Machine learning is concerned about

constructing programs that automatically
learn from experience/past data

Data Science uses Machine learning

Algorithms to create useful products based
on available data.

Source: https://blog.finxter.com/
Key areas where AI can make a significant impact
(Considering ever increasing human population)
→ Resource management and optimization

→ Agriculture and food production

→ Healthcare

→ Urban planning and transportation

→ Education

→ Environmental conservation

→ Family planning and reproductive health

Explainable AI

→ is designed to explain its decisions, results, and processes to humans in a way that
they can understand.

→ commonly used in settings where transparency is key, such as in healthcare,

financial services, judiciary, and the public sector

→ For example, explainable AI in the judiciary is vital for maintaining transparency,

fairness, and trust in legal processes
Responsible AI

→ a philosophy and set of principles that promotes the use of AI in an

ethical manner

→ seeks to ensure that AI is used in a way that respects human rights,

maintains fairness, transparency, and accountability

→ avoids potential harms and harms to individuals, communities, and the

environment

→ designed to be as safe and secure as possible.

AI and Ethics

→ use of AI algorithms (based on biased data), in hiring and recruitment processes. In

2018, it was reported that Amazon scrapped an AI-based recruiting tool because it
was biased against female candidates.

→ COMPAS an AI tool used in various U.S. jurisdictions for pretrial and sentencing
evaluations displayed racial bias, with Black defendants being more likely to be
falsely labelled as high risk for reoffending, while White defendants were more
likely to be incorrectly labelled as low risk.
Sofia(a humanoid robot): Weak AI or Strong AI ?

• The Sofia humanoid robot was

developed by Hanson Robotics, a
Hong Kong-based engineering and
robotics company founded by Dr.
David Hanson.
• Sofia was first activated in 2016 and
has since become one of the most
famous and recognizable robots in
the world, known for its lifelike
appearance and advanced AI
capabilities. Hanson Robotics humanoid Robot Sophia.
https://www.youtube.com/watch?v=G-zyTlZQYpE
Top 10 AI websites
1. OpenAI (https://www.openai.com):

2. Google AI (https://ai.google):

3. DeepMind (https://www.deepmind.com): I

4. IBM Watson (https://www.ibm.com/watson):

5. NVIDIA AI (https://www.nvidia.com/en-us/ai-data-science):

6. Microsoft AI (https://www.microsoft.com/en-us/ai):

7. Facebook AI (https://ai.facebook.com

8. Baidu Research (http://research.baidu.com):

9. AI Hub (https://aihub.cloud.google.com):

10. MIT CSAIL (https://www.csail.mit.edu):

 → Siri, Alexa and other smart assistants

Examples of → Self-driving cars

AI Based → Robo-advisors

→ Conversational bots
Products → Email spam filters
→ Amazon’s recommendations
Some interesting AI products

→ AI model with language capabilities

→ AI system that can create realistic images and art from a description in natural
language. https://openai.com/product/dall-e-2

→ Create a fake videos https://deepfakesweb.com/

→ Create Fake photos of people https://this-person-does-not-exist.com/en

→ Create music https://soundraw.io/

→ AI model to offer coding suggestions https: //github.com/features/copilot

 Deep Learning

→ Deep learning is a type of machine learning that uses artificial

neural networks, which are computer systems modelled after
the human brain, to learn from large amounts of data.
Fake videos generation – Beware of its risks
→ Deepfakes have been used to break down linguistic barriers, including by English soccer
great David Beckham in his Malaria No More campaign, where deepfakes enabled him to
deliver his message in nine different languages.

→ Mark Zuckerberg, founder of Facebook reveals the ‘truth’ about privacy on Facebook
(2019).

https://www.instagram.com/p/BypkGIvFfGZ/?utm_source=ig_embed&utm_campaign=embed_
video_watch_again

→ Introduction to Deep Learning (MIT Video)

https://www.youtube.com/watch?v=5tvmMX8r_OM&list=PLtBw6njQRU-
rwp5__7C0oIVt26ZgjG9NI
ChatGPT

→ As an AI language model, ChatGPT generates text based on patterns it has learned

from large amounts of data.

→ While ChatGPT is capable of generating informative and useful responses, it is also

possible for it to produce inaccurate or false information in some cases.

→ This can happen if the data used to train the model contains errors or biases, or if
the model misinterprets the input data.
Capabilities of ChatGPT

1. Natural language understanding

2. Natural language generation

3. Information retrieval:

4. Conversation: (maintaining context and relevance)

5. Summarization:

6. Text completion and expansion:

7. Translation:

8. Creative writing:

9. Language-based tasks:
AI Applications and Risks in Using AI

→ Judiciary : may lead to decisions that are not based on justice and fairness (due to bias of the data
set)

→ Autonomous/Self-driving Vehicles: can raise ethical and legal questions, such as who is held
responsible for any accidents that occur due to the AI system’s decisions.

→ Robotics: are vulnerable to hacking, could be used to create physical harm or damage, either
intentionally or unintentionally, might be used to carry out activities that are socially or morally
wrong , due to their lack of understanding of the complexities of human behaviour

→ Healthcare: Using AI in healthcare can present a number of risks. AI systems may not be able to
detect all the medical conditions, leading to missed diagnoses or inaccurate treatments.

→ Military: AI-powered systems could cause unintended damage if they malfunction or misfire. This
could lead to harm to civilians and property, as well as harm to military personnel
Tesla unveils new AI for humanoid robots called 'Optimus’
(Launched in 2022)

https://abcnews.go.com/GMA/News/video/tesla-unveils-ai-humanoid-robots-called-optimus-
90819056
Will AI increase unemployment ?

→ Artificial intelligence could displace roughly 15% of workers, or 400 million

people, worldwide between 2016 and 2030, according to a McKinsey study.

→ In a scenario of wide AI adoption, the share of jobs displaced could rise to as much
as 30%

→ workers in low-wage and low-skill occupations may be more vulnerable to job loss
than those in high-wage and high-skill occupations.

→ As AI continues to transform the job market, workers may need to acquire new
skills and knowledge in order to remain employable.
Conclusion
→ the use of AI for mankind will be safe only if the AI developers follow ethical
practices and takes utmost care in selecting the authentic data on which it is trained.

→ AI model must be thoroughly tested for any lapses before it is deployed for the use
by human beings.

→ In future, Governments across the globe need to device regulations and safety
standards for such AI based applications and gadgets

→ Although AI poses the risk of displacement of job opportunities, it has tremendous

potential for betterment of man kind amid ever increasing human population

→ Learning AI tools and Technologies will give you better job opportunities
Poem on Artificial Intelligence

(Generated by Chat GPT)

Thank You

email:[email protected]