By the Power of Grayscale
51–56 of 56 posts
Re: By the Power of Grayscale
#52Earlier quoted context omitted.
Classical machine vision and pattern recognition is absolutely AI. Or at least it was AI before it became too mature to be called that. As they say, any AI problem that gets solved stops being AI and becomes just normal algorithmics.
Classical computer vision is no more AI than quicksort or BFS is. What they say is ML is AI that works. But classic computer vision (CV) is hand rolled algorithms like Eigenfaces to detect faces or Mixture of Gaussians for background subtraction. There's no magic black box model in classic CV, no training on data, no generated pile of "if"s that no one knows how it works. Just linear algebra written and implemented b…
ML, at least historically, has been considered a subset of AI, not a superset.
Until the rise of LLMs recently using human-designed deterministic algorithms to perform ‘intelligent’ tasks (like image processing, and especially image recognition) has absolutely been considered AI.
AI encompasses (encompassed?...) everything that uses computation to produce intelligence-like results.
I fear the terminology battle has been lost, though, and nowadays most people consider at least neural networks - perhaps also non-determinism of output - to be a prerequisite for something being “AI” - which is actually _less_ meaningful to the end-user.
Re: By the Power of Grayscale
#53Earlier quoted context omitted.
Classical machine vision and pattern recognition is absolutely AI. Or at least it was AI before it became too mature to be called that. As they say, any AI problem that gets solved stops being AI and becomes just normal algorithmics.
Classical computer vision is no more AI than quicksort or BFS is. What they say is ML is AI that works. But classic computer vision (CV) is hand rolled algorithms like Eigenfaces to detect faces or Mixture of Gaussians for background subtraction. There's no magic black box model in classic CV, no training on data, no generated pile of "if"s that no one knows how it works. Just linear algebra written and implemented b…
You’re moving the goalposts, which is exactly what I referred to. Search algorithms and pathfinding have absolutely been AI historically, just go take a look at the table of contents of Norvig’s AI:MA. And I mean the 4rd edition that was published in 2020. A good 90% of the book is classical algorithmics.
It’s pretty hilarious and history-blind to claim that AI is just 2015+ era deep neural magic black boxes or something, as if the field wasn’t invented until then. As if neural networks themselves hadn’t been tried several times at that point and found okay for classification tasks but not much more.
As if for a long time, most AI researchers didn’t even want to talk about neural networks because they feared that their "cool" factor takes focus away from real AI research, and because the last time NNs were a big deal it was followed by one of the AI winters of broken promises and dwindling budgets.
Re: By the Power of Grayscale
#54Earlier quoted context omitted.
Classical computer vision is no more AI than quicksort or BFS is. What they say is ML is AI that works. But classic computer vision (CV) is hand rolled algorithms like Eigenfaces to detect faces or Mixture of Gaussians for background subtraction. There's no magic black box model in classic CV, no training on data, no generated pile of "if"s that no one knows how it works. Just linear algebra written and implemented b…
You’re moving the goalposts, which is exactly what I referred to. Search algorithms and pathfinding have absolutely been AI historically, just go take a look at the table of contents of Norvig’s AI:MA. And I mean the 4rd edition that was published in 2020. A good 90% of the book is classical algorithmics. It’s pretty hilarious and history-blind to claim that AI is just 2015+ era deep neural magic black boxes or somet…
> It’s pretty hilarious and history-blind to claim that AI is just 2015+ era deep neural magic black boxes or something, as if the field wasn’t invented until then.
I didn't make that claim. Was this written by a hallucinating LLM?
Re: By the Power of Grayscale
#55So, who is He-Man, and who is Skelator?
Re: By the Power of Grayscale
#56Earlier quoted context omitted.
Not to mention performance. So often, the traditional method is the only thing that can keep up with performance requirements without needing massive hardware upgrades. Counter intuitively, I’ve often found that CNNs are worse at thresholding in many circumstances than a simple otsu or adaptive threshold. My usual technique is to use the least complex algorithm and work my way up the ladder only when needed.
Something I've had a lot of success with (in cases where you're automating the same task with the same lighting) is having a human operator manually choose a variety of in-sample and out-of-sample regions, ideally with some of those being near real boundaries. Then train a (very simple -- details matter, but not a ton) local model to operate on small image patches and output probabilities for each pixel. One fun thin…
I’ve done that too. In essence it kinda sorta comes down to a small convolution kernel with learned weights.
In some places it works really well.