31–40 of 235 posts
Can someone break this down for this layman?
Wow: "In this work, we show that, contrary to expectations, a great deal of image statistics are captured by the structure of a convolutional image generator rather than by any learned capability. This is particularly true for the statistics required to solve various image restoration problems, where the image prior is required to integrate information lost in the degradation processes. To show this, we apply untrain…
> PS. This makes me wonder whether and to what degree the structure of the brain's connectome is a necessary prior for AGI. Well, I wouldn't mix up AGI and AGI by deep learning, and more important I would emphasise that this is a good prior for images . The fundamental insight in CNNs and eventually in this work is that there is a correlation between pairs of nearby pixels. We have something similar for video and aud…
Can someone break this down for this layman?
It seems that the current accepted method is to train a network with distorted images as the input and the correct undistorted images as the targets. Then after training you can feed a new distorted image into the trained network and get the estimated "fixed" image.
However this team actually uses the distorted image as both the input and the target to the net. So if they were to let the training go on for too long the network will produce an exact copy of the distorted input image. But for some reason, the structure of the network means that the estimated output learns realistic features first, and then overfits to the noise afterwords. So if you stop the training early, you get an image that incorporates realistic features from the distorted image, but hasn't had time to "learn" the noisy features.
Can someone break this down for this layman?
The structure of convolutional neural nets specifies much of the prior knowledge necessary for learning. In other words, the design of these neural nets makes a lot of correct assumptions about the nature of images (stationarity of pixel statistics, locality of pixel dependencies, and so on).
Do they run some kind of optimizer to learn the optimal CNN structure or does some person sit down and pick structures to include in it?
Earlier quoted context omitted.
The structure of convolutional neural nets specifies much of the prior knowledge necessary for learning. In other words, the design of these neural nets makes a lot of correct assumptions about the nature of images (stationarity of pixel statistics, locality of pixel dependencies, and so on).
is the structure of these CNNs learned or designed? Do they run some kind of optimizer to learn the optimal CNN structure or does some person sit down and pick structures to include in it?
Can someone break this down for this layman?
Neural networks are powerful without even training them. By merely designing the structure of them you are creating something.
Sussman attains enlightenment
In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6.
“What are you doing?”, asked Minsky.
“I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied.
“Why is the net wired randomly?”, asked Minsky.
“I do not want it to have any preconceptions of how to play”, Sussman said.
Minsky then shut his eyes.
“Why do you close your eyes?”, Sussman asked his teacher.
“So that the room will be empty.”
At that moment, Sussman was enlightened.
Can someone break this down for this layman?