Reasoning is what you use to make sense of things that aren't a simple interpolation of things you've seen before.
@fchollet
-
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.
-
Keras Lookup Layers Store Vocabulary as Inspectable Plaintext Files
By
–
…as well as custom assets written by layers that manage non-numerical state, such as vocabulary text files. Keras lookup layers store their vocabulary files as plaintext, so you can inspect and reuse them in a new context.
-
White-box model format: JSON config and weights in ZIP archive
By
–
The format is entirely whitebox — the file saved is a zip archive that you can inspect. It contains the config of the model as a human-readable JSON file (a description of the architecture and hyperparameters of the model), a weights file (essentially a dict of arrays)…