But if you're given a similar problem again and again… then you'll start noticing patterns. Maybe you'll become able to make a pretty good guess just from the look & feel of the drawers. Despite the strange format, the problem will become just another pattern recognition task.
@fchollet
-
Using Shape Equations to Predict Pixel Colors and Solve Problems
By
–
You're going to have to use the shape equations to make predictions about the color of certain pixel coordinates, find discriminative ones, and fetch the corresponding cubes from the drawers to make a conclusion. (One of several possible methods you could come up with!)
-
Reasoning: Making Sense Beyond Simple Interpolation
By
–
Reasoning is what you use to make sense of things that aren't a simple interpolation of things you've seen before.
-
Reasoning versus pattern recognition in novel problem forms
By
–
You'd have to use reasoning if the problem comes in a form that you've never seen before, that renders your pattern recognition ability ineffective. Let's say the task specification comes in the form of shape equations in the 2D plane, and your images come in the form of…
-
Reasoning in Visual Perception: Distinguishing Squares from Circles
By
–
The former sounds perhaps stranger, so here's an example. Let's say you have to tell whether a given image contains a square or a circle — a canonical perception problem. Sounds easy enough if you have a well-trained visual system, right? How would reasoning come into play?
-
Perception vs Reasoning: Data Volume Determines Problem-Solving Approach
By
–
Any task, even those canonically considered to be perception problems, can be solved with reasoning (if working with very little data). Inversely any task, even those canonically considered to be reasoning problems, can be solved with pattern recognition (given sufficient data).
-
Bot Problem Illustration in Thread Discussion
By
–
Illustration of the bot problem right in this thread
-
New model.export() API for optimized inference-only model export
By
–
In the coming months, you will also have access to a `model.export()` API for inference-only model export, relying on the SavedModel format. It will include options for target-specific optimizations — think mobile, browser, microcontrollers, etc.
-
New .keras file format introduction and testing request
By
–
This new file format is new, so please try it out, and if you run into any issues, please report them on GitHub! In the coming months, we will make this format the new default for any file with the `.keras` extension.