21–30 of 116 posts
Why can't you just train the network on artificially altered photos, with "elephants" randomly scattered around, until it is robust to them?
Why can't you just train the network on artificially altered photos, with "elephants" randomly scattered around, until it is robust to them?
To an extent it shows the gap between neural networks being able to classify things, and actually being able to understand what they are seeing, which will always limit their utility beyond classifying images that look like other images they've seen before.
Why can't you just train the network on artificially altered photos, with "elephants" randomly scattered around, until it is robust to them?
Because there's always another type of 'elephant' to be thrown in. The networks are just not inherently robust against unexpected features (I'll call them outliers for want of a better term), and this is what needs to be fixed, and not increasing the variety and frequency of outliers.
Earlier quoted context omitted.
Because there's always another type of 'elephant' to be thrown in. The networks are just not inherently robust against unexpected features (I'll call them outliers for want of a better term), and this is what needs to be fixed, and not increasing the variety and frequency of outliers.
Doesn’t increasing the frequency and variety of outliers just make them no longer outliers?
Can't they implement a "virtual representation" or sort of ideal or archetypical scene in an AIs memory that's quickly accessible, and then use that to diff "new unexpected stuff" and refocus on that difference somehow?
Why can't you just train the network on artificially altered photos, with "elephants" randomly scattered around, until it is robust to them?
Are you going to repeat this with every object that exists, or could exist?
Earlier quoted context omitted.
Parent is not sarcastic. Automated recognition systems are systems , which means they are made of several components (sensors, databases, hardwares, softwares) working together. Neural networks are one of those sub-components and no one ever claimed that neural networks are 100% accurate and sufficient to build automated decision systems. The problem described in the article is taken into account when building system…
The problem described in the article is taken into account when building systems (like autonomous cars) using neural networks. Where can I find more information on this?
Keywords are "control theory", "sensor fusion", "automated decision under uncertainty" that you can look on Google, Wikipedia and arXiv. Also "Simultaneous localization and mapping" which is a good example of using uncertain data points from different sensors to build a representation of the reality.
In those systems, a neural network is just another sensor providing augmented information.
Why can't you just train the network on artificially altered photos, with "elephants" randomly scattered around, until it is robust to them?
Are you going to repeat this with every object that exists, or could exist?
Earlier quoted context omitted.
Are you going to repeat this with every object that exists, or could exist?
No, you see neural networks are specially afraid of elephants. Just like elephants are especially afraid of mice. And so the circle continues, all the way around to humans who are especially afraid of neural networks and what they will do to society.
What if an algorithm actually had a focused sight? Look at the brightest feature, blur the rest, then try to find another distinctive details, look closer into the parts of the image until the most of it becomes clear. Let other neural network control the scanning process and loop until it develops some confidence in the result. Can it work that way?