When did the AI surge begin?
Back in the 1800s, AI was limited
in myths, fiction, and speculation. Classical philosophers envisioned machines
integrated into human beings. However, they were just portrayed in fiction work
like Mary Shelly’s “Frankenstein” then. The real initiation in AI began in
1956. The seed that led towards an AI future was a workshop in Darthmod
College, attendees of which were claimed as AI leaders for decades to
come.
The AI surge began with six major
design goals as follows:
- Teach machines to reason in
accordance to perform sophisticated mental tasks like playing chess,
proving mathematical theorems, and others.
- Knowledge representation for
machines to interact with the real world as humans do — machines needed to
be able to identify objects, people, and languages. Programming language
Lisp was developed for this very purpose.
- Teach machines to plan and
navigate around the world we live in. With this, machines could
autonomously move around by navigating themselves.
- Enable machines to process
natural language so that they can understand language, conversations and
the context of speech.
- Train machines to perceive
the way humans do- touch, feel, sight, hearing, and taste.
- General Intelligence that
included emotional intelligence, intuition, and creativity.
All these goals set the
foundation to build a machine with human capabilities. Millions of dollars were
invested in bringing their vision to life. However, soon, the US government
realized the absence of powerful computing technologies needed to implement AI.
The funds were withdrawn, and the journey took the first halt in the late 80s.
The need for a massive amount of
data and enormous computing power disrupted the progress in the 80s. The 21st
century, however, brought the concept quickly back to life proving Moore’s law. The heavy processing power that tiny
silicons hold today has made AI feasible in the current context, also enabling
to build improved algorithms.
There have been four successive
catalysts in the AI rebirth and revolution:
- The democratization of AI
knowledge that began when world-class research contents were made
available to the masses- starting with MOOCs from Stanford University with
Andrew NG and Intro to ML by Sebastian Thurn and Katie Malone from Udacity.
- Data and Computing Power
(cloud and GPU) that made AI accessible to the masses without enormous
upfront investment or being a mega-corporation.
- Even with access to data and
computing power, you had to be an AI specialist to leverage it. However,
in 2015, there was a proliferation of new tools and frameworks that made
exploring and operationalizing production-level AI feasible to the masses.
You can now build on the backs of giants like Google (Tensorflow),
and Facebook( PyTorch). Numerous organizations have been founded
with the democratization of AI like FastAI and OpenAI.
- In the past two years, AI as a service has taken this a step further, enabling easier prototyping, exploration, and even building sophisticated and intelligent use-case specific AI’s in the product. There are platforms like Azure AI, AWS AI, Google Cloud AI, IBM Cloud AI, and many more that provides AI as a Service.
No comments:
Post a Comment