 |
| Photo by Alex Knight from Pexels |
How does Artificial intelligence A.I learn ?
Today's artificial intelligence helps doctors diagnose patients pilots fly commercial aircraft and city planners predict traffic no matter what these guys are doing the computer scientists who designed them like we don't know exactly how they're doing this is because artificial intelligence is often self taught working off a simple set of instructions to create a unique array of rules and strategy. So how exactly does a machine.
There are many different ways to build self teaching program but they all rely on the 3 basic types of machine learning unsupervised learning supervised learning and reinforcement. To see these in action let's imagine researchers are trying to pull information from a set of medical data containing thousands of patient profile. First up unsupervised learning. This approach would be ideal for analyzing all the profiles to find general similarities and useful patterns maybe certain patients have similar disease presentations or perhaps a treatment produces specific sets of side.
This broad pattern seeking approach can be used to identify similarities between patient profiles and find emerging patterns all without human guidance let's imagine doctors are looking for something more specific these physicians want to create an algorithm for diagnosing a particular condition. They begin by collecting 2 sets of data medical images in test results from both healthy patients and those diagnosed the condition. Then they input this data into a program designed to identify features shared by the 6 patients not the healthy patients based on how frequently it sees certain features the program will assign values to those features diagnostic significance generating algorithm for diagnosing future patients however unlike unsupervised learning doctors a computer scientists have an active role in what happens next doctors will make the final diagnosis and check the accuracy of the algorithm's predictions.
Then computer scientists can use the updated data sets to adjust the program's parameters and improve it's accuracy this hands on approach is called supervised learning now let's say these doctors want to design another algorithm to recommend treatment plan since these plans will be implemented in stages and they may change depending on each individual's response to treat. The doctors decide to use reinforcement learning this program uses an iterative approach to gather feedback about which medications dosages and treatments are most effective then it compares that data against each patient's profile to create their unique optimal treatment plan as the treatments progress in the program receives more feedback it can constantly update the plan for each patient. None of these 3 techniques are inherently smarter than any other while some require more or less human intervention they all have their own strengths and weaknesses which makes invested it for certain tasks however by using them together researchers can build complex AI systems for individual programs can supervise and teach each other for example when are unsupervised learning program finds groups patients that are similar you can send that data to a connected supervised learning program.
That program could then incorporate this information into its predictions or perhaps dozens of reinforcement learning programs might simulate potential patient outcomes to collect feedback about different treatment plans there are numerous ways to create these machine learning systems and perhaps the most promising models are those that mimic the relationship between neurons in the brain these artificial neural networks can use millions of connections to tackle difficult tasks like image recognition speech recognition and even language translation however the more self directed these models becomes the harder it is for computer scientists to determine how the self taught algorithms are private their solution researchers are already looking at ways to make machine learning more transparent but as a I. D. comes more involved in our everyday lives these enigmatic decisions have increasingly large impact on our work health and safety. So as machines continue learning to investigate the Goshen and communicate we must also consider how to teach them to teach each other to operate.
Today's computers can pilot space craft and perform surgery but according to computer scientist Alan Turing the real test of a computer's intelligence is basic small talk check out this video to find out why.
0 Comments