Harsh
  • Member for 5 years, 5 months
  • Last seen more than 1 year ago
What exactly are genetic algorithms and what sort of problems are they good for?
7 votes

There are a number of good answers here explaining what genetic algorithms are, and giving example applications. I'm adding some general purpose advice on what they are good for, but also cases where ...

View answer
Which artificial neural network can mimic biological neurons the most?
1 votes

Most artificial neurons model biological neurons but in a very simplistic way. Nowadays, the main aim is to achieve better performance at prediction tasks. However, there is a body of literature in ...

View answer
Is Lisp still being used to tackle AI problems?
Accepted answer
10 votes

Overall, the answer is no, but the current paradigms owe a lot to LISP. The language most commonly used today is python. Relevant answers: Stack Overflow thread explaining why LISP was thought of as ...

View answer
Could AIs self-develop in the future?
2 votes

This is known as the intelligence explosion hypothesis or recursive self-improvement.

View answer
What artificial intelligence strategies are useful for summarization?
Accepted answer
7 votes

The following post has a bit of math, which I hope helps to explain the problem better. Unfortunately it seems, this SE site does not support LaTex: Document summarization is very much an open ...

View answer
Does this argument refuting the existence of superintelligence work?
0 votes

The flaw in your argument is that "surpass" doesn't just mean that you should be able to run all algorithms, it includes a notion of complexity, i.e. how many time steps you will take to simulate an ...

View answer
What research has been done in the domain of "identifying sarcasm in text"?
Accepted answer
5 votes

The following survey article by researchers from IIT Bombay summarizes recent advances in sarcasm detection: Arxiv link. In reference to your question, I do not think it is considered either ...

View answer
Is there a way to define the boundaries of the optimal size of a training set?
1 votes

In general, the larger the training set, the better. See The Unreasonable effectiveness of Data, though this article is quite dated (written in 2009). Xavier Amatriain, a researcher at Netflix has a ...

View answer
How could self-driving cars make ethical decisions about who to kill?
16 votes

This is the well known Trolley Problem. As Ben N said, people disagree on the right course of action for trolley problem scenarios, but it should be noted that with self-driving cars, reliability is ...

View answer
How is it possible that deep neural networks are so easily fooled?
11 votes

An important question that does not yet have a satisfactory answer in neural network research is how DNNs come up with the predictions they offer. DNNs effectively work (though not exactly) by ...

View answer
What limits, if any, does the halting problem put on Artificial Intelligence?
12 votes

The halting problem is an example of a general phenomenon known as Undecidability, which shows that there are problems no Turing machine can solve in finite time. Let's consider the generalization ...

View answer
What are the challenges for recognising the handwritten characters?
Accepted answer
6 votes

Handwritten digit recognition is a standard benchmark in Machine Learning in the form of the MNIST dataset. For example, scikit-learn, a python package for Machine Learning uses it as a tutorial ...

View answer