How to build a robot that “sees” with $100 and TensorFlow
oreilly.com
oreilly.com
One may also call the localization of the object as object detection and subsequent classification.
But I don't think it's too important how we call it as long as we understand what the task is.
The system has to segment before it classifies. That isn't returned to the user, but gradient descent is happening in the background. Like I said, it's a nitpick but important if you're trying to really build novel CV applications.
One of my gripes with people implementing pre-built modules from TF is that you don't really build any of the hard stuff, and it's pre-trained so not much learning is happening. You can't for example build RL systems with off the shelf TF implementations.
Also gradient descent has nothing to do with segmentation at all, I don't understand what you're talking about. Gradient descent is used to find the set of weights that minimizes the error. This is standard in training neural networks of any kind using backpropagation.
The Holy Grail is general AI. Recognizing objects is a side quest, perhaps a required step, but, by no means, the end goal.
I get that a lot of people downplay achievements in machine learning by saying it's nothing like AGI, but it's almost a meme now that "once upon a time everyone thought that was the holy grail and they're moving the signposts" even when 1) nobody thought that, or 2) some people thought that and some people didn't think that.
Even today, it's hard to make laymen appreciate the advancements in computer vision because for them "seeing" doesn't seem like a difficult thing. Even stupid chickens can see. A chess program is much more impressive to laypeople.
The ability to recognize objects like people do is not properly represented by current benchmarks. I can imagine that you can built a perfect robotic "bird spotter" but if you put that in a self-driving car I would not be surprised if it stops for something that's just a shadow, or if you put it on a humanoid it's unable to distinguish its own hand from that of its clone. Imagine two of them cleaning out the dishwasher. :-)
A lot of AI is still working only in lab conditions or restricted application domains. That's why I consider robots and cars so important in driving AI towards the "general" dimension.
There have been some improvements but they are incremental indeed. More use of ReLU, dropout etc. But it's not a new paradigm at all.
But the idea of neural nets is very old, going back to Rosenblatt and connectionism.
And general common sense reasoning.
I was at one time guilty of this. But hey, I was young and stupid :D
I'm pretty sure we'll eventually learn to do anything without AGI, as a narrow task.
The trick with AGI is putting all those little things together. Perhaps that's the actual recipe for it, somehow. Turtles all the way down, who knows how many levels.
(Then again, I'm biased.)
https://www.tensorflow.org/versions/r0.10/tutorials/image_re...
https://d3ansictanv2wj.cloudfront.net/Figure_2-985cd20ea0c0b...
Robot manipulation in unstructured situations still sucks, though. Willow Garage was making progress, but didn't last.
So, not autonomous it would seem. With that and an arm, though, you could eventually get it to play fetch...
If you promise not to judge me, you can use anything at your own risk here: https://github.com/lukas/robot
http://www.seattlerobotics.org/encoder/jan97/lowresv.html
It was a fantastic resource and I bet it was a lot of work to put one together. I sure appreciated the people that took the time to make it.
I always wanted to find some way to get to one of their meetings but it never worked out.
I'm still soldering wires into the motors. You should take off the paper from acrylic. The transparent effect makes it look awesome.
My goal is to make a raspberry pi bot that plays indoor fetch. I would love to have a chat with you.
With Chrome developer tools I see one error: "Uncaught SecurityError: Failed to read the 'localStorage' property from 'Window': Access is denied for this document."