Ready to learn Machine Learning? Browse courses like Machine Learning Foundations: Supervised Learning developed by industry thought leaders and Experfy in Harvard Innovation Lab.
Artificial Intelligence (AI) is hardly in its infancy stage. It is not that accessible and thus the AI based solutions that we are using or are being deployed are far inferior to what we expect in the next two to three decades. We have experienced quite a lot of users express their frustration on Chatbots.
All major Chatbots aren’t actually intelligent. They are built based on decision-tree logic, algorithms and thought concepts, where the response given by the bot depends on specific keywords that are identified in the user’s input. Now if the user’s input contains ‘DSLR’ then a Chatbot would often send a message with a never-ending product list. Now if the user provides the ‘BRAND NAME’ the Chatbot would still provide a big list of DSLRs that the brand owns. In this case the User would immediately leave the Chat interface and rather logon to the online portal do do things manually since that would save his time and efforts.
Even your so called Online Personal Assistants who are said to be “intelligent interface to everything” struggle with a lot of questions and all one gets to hear is the message that “Sorry I do not understand. I am learning new things daily and trying my best to improve my knowledge”. This also means that these bots are not even able to make the most out of strong Search Engines optimally. When technology fails, users still want to be able to rely on human beings to help them solve their problems. In case of emergency or in situations where the bots fail to provide an answer, they lack proper human escalation protocols. This often leads to a loss of opportunity or gain for some other competitor who might be slightly better. Thus we can conclude that despite the best of our intentions, Chatbots or online personal assistants fail to deliver user experiences that are as seamless, delightful and efficient as we expect them to be.
Unfortunately the bots are as good as the designer/programmer who created it to anticipate all potential user use cases and inputs. AI experts are often directionless. They fail to explore Cognition, Neural Networks before creating Artificial Neural Networks (ANNs) and exploring User Behavior Analytics (UBA). Bots with linguistic and natural language learning, speech-detection and flawless information processing capabilities are still quite rare. It is quite natural that many companies are trying to be the first in their category to successfully deploy an innovation. Sadly that mad rush is forcing us to see a plethora of bots that are offering poor to miserable experiences. This was expected, our industry will learn from its failures before it is able to deploy bots that are truly intelligent and are capable of doing things.
On the other hand although UBA is doing wonders for e-commerce and retail, Search Engine Optimization (SEO) that is either manual or AI based, seems to be a huge failure at the moment. When you use an online search engine you have to work out what you are looking for and the words to use to find it. That will move to the search engine having data on you to give you customized searches. This data need not be necessarily accurate thanks to AI based SEO and padded manual SEO. Now, this is some big story. If you think, you know how SEO and UBA works, you actually might not know anything about it.
AI in Web-mapping / Geo Information Systems (GIS) is yet to achieve 50 percent accuracy forget cent percent. Big Data Analytics (BDA) could provide real time inputs but human efforts are much required till AI reaches Singularity. It is often frustrating, to book a car from one of the online cab aggregators (OCAs) and then face a delay of 15 minutes because of a GIS failure. This failure also creates hindrance in speeding up an OCAs progress in creating self-driving cars. Flying cars is still a distant dream although we are right there. At times when one books a car, its miles away when one could have got a car that was standing right there. The fact is that the programmers that decide the logic still don’t know why AI makes one decision over another.
A lot of online housekeeping tasks have been successfully taken over by the bots but we do need human supervision to achieve precision. Two AI bots could often fight each other if pitted that way, and this fight could last for centuries the way we look at AI right now. In many cases, the bots get into a conflict mode because they followed slightly different rules to one another. All this indicates that AI needs strong leadership; a leader who can set the direction, control and govern the very innovation.
