71–80 of 114 posts
After rotating the image 90 degrees, the predicted result changes substantially. The author should not be surprised. A convolutional neural network is translationally invariant, not rotationally invariant.
For context, ImageNet does have a sofa category for labels :/ http://image-net.org/search?q=sofa
There are no sofa's in this list, the closest thing I can find is a "studio couch, day bed": http://imagenet.stanford.edu/synset?wnid=n04344873
On the other hand, nobody has been upset that humans are constantly misidentifying that jaguar print sofa as a leopard print.
If one paired the present classifiers with Amazon Mechanical Turk, just providing one bit of information -- "is-it-an-animal?" -- I wonder how well the current classifiers would fare in relation to human beings?
(1) - Ironically, the more "cosmopolitan" people become, the quicker they are to jump to such conclusions!
Somehow tangent but this made me think about this quote found on HN last year: Context: Evolutionary algorithms and analog electronic circuits > One thing stands out when you try playing with evolutionary systems. Evolution is _really_ good at gaming the system. Unless you are very careful at specifying all of the constraints that you care about you can end up with a solution that is very clever but not quite what yo…
There's an alife program called DarwinBots where small bots powered by mutating code compete against each other to survive and reproduce. Given enough time, you'd expect the to develop clever behaviors, but instead they just fuzz-tested the sim and locked in on exploits of bugs or environment settings. They only got a bit more clever when connecting different sims running on different conditions. Eyes already use dif…
Classic A-life! Also, not so different from the spirit of actual biology.
They only got a bit more clever when connecting different sims running on different conditions.
Diversity is very important for evolution on many levels. What many don't realize (especially, I note, evolution deniers) is that the ecosystem as a whole provides a very complex and continually varying epiphenomenal fitness function to any given organism.
This article would not come as a surprise to anyone who works with ConvNets. Sadly, that might not the case for those outside of the field, largely due to media's inadequate coverage of our advances (but this is common outside our field too). No one in the field really believes ConvNets see better than humans. They are very good single glance texture recognizers. It's as if you flashed an image and looked at it for a…
So I wonder to what extent you would consider this a predictable outcome from the classifier in question not being part of a subsumptive architecture --- which at a guess would look like
- glance/texture responses fed into
- boundary-recognition layers fed into
- object persistence/tracking layers
- fed into abstract scene reasoning
[1] https://en.wikipedia.org/?title=Subsumption_architecture
[2] I realize this may seem, superficially, anathema to deep network research, which advocates letting the network find its own intermediate levels of abstraction. But it's actually compatible in my view because Brooks advocates (again, paraphrasing quite a bit) that the separate layers should have different objective functions, and that in fact the need for different objective functions (in a prioritized order) is the cause of emergent layering in nature. "First, don't die. Second, find shelter. Third, find food etc." So one can imagine deep networks each finding their own locally useful abstractions for each objective function in the "Maslow" chain, while still having some macro architecture that tracks human-imposed design principles.
Earlier quoted context omitted.
Who is Terry Davis.
I didn't know either, but found this: http://motherboard.vice.com/read/gods-lonely-programmer Scary and fascinating.
This article would not come as a surprise to anyone who works with ConvNets. Sadly, that might not the case for those outside of the field, largely due to media's inadequate coverage of our advances (but this is common outside our field too). No one in the field really believes ConvNets see better than humans. They are very good single glance texture recognizers. It's as if you flashed an image and looked at it for a…
Might you by chance be familiar with Rodney Brooks' work on subsumption architectures [1]? If not, I would summarize the underlying idea (my words not his) as "don't try to jump too many layers of abstraction in one go" [2]. So I wonder to what extent you would consider this a predictable outcome from the classifier in question not being part of a subsumptive architecture --- which at a guess would look like - glance…
the problem is.. human vision doesn't work just by feeding a bitmap. we have structure to decode space relationships, shapes and maybe even shadow/light relations. no way we gonna see classificator working on color arrays matching our vision capabilities
Earlier quoted context omitted.
Next step is Video. Adding temporal dimension will emphasize extrapolating true 3d shapes of recognized objects.
Not just 3D shapes, but understand actions as they develop in time with recurrent neural networks.
It seems that this is more like the way that we learn to identify things. Then once we establish an understanding of a base class (big cat) we can apply that same model to new cats that we have never seen before with just a picture.
Thank you for this article; very thought provoking. My nitpick: > When each student was given a heavy book of MNIST database, hundreds of pages filled with endless hand-written digit series, 60000 total, written in different styles, bold or italic, distinctly or sketchy. > ... > So, are you going to say that was not the case? I understand the point the author is making. Human brains are really good at taking limited…
You can show me novel symbols, with me only looking at a single example of each for a few seconds, and I can manage good categorization.