deep-rules

deep-rules copied to clipboard

Fairly validate your model with proper test/train data

6

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule. ) to see if the rule has already been proposed?** - [X] Yes **Feel free to elaborate, rant, and/or ramble.** **Any citations...

chevrm

Don't use deep learning if you don't have to.

5

Oftentimes, deep learning is not the best approach. I think one rule (possibly even the first in the article) should be a warning against using DL when it's not needed.

Benjamin-Lee

Use training/tuning/testing dataset terminology

11

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule) to see if the rule has already been proposed?** - [x] Yes **Did you add yourself as a [contributor](https://github.com/Benjamin-Lee/deep-rules/blob/master/contributors.md) by making a...

michaelmhoffman

Be suspicious: high prediction accuracy may backfire

1

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule) to see if the rule has already been proposed?** - [x] Yes **Did you add yourself as a [contributor](https://github.com/Benjamin-Lee/deep-rules/blob/master/contributors.md) by making a...

HaohanWang

There's more than one way to do it: find the learning that's right for you (and your data)

3

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule) to see if the rule has already been proposed?** - [X] Yes **Feel free to elaborate, rant, and/or ramble.** **Any citations for...

chevrm

If a human can't perform the task with ease, be surprised if a machine can.

11

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule) to see if the rule has already been proposed?** - [x] Yes **Feel free to elaborate, rant, and/or ramble.** Alternative heading: Garbage...

paulbrodersen

If you don't have enough data, consider whether there is other data that can help pre-train a model.

2

Often we lack a large amount of labeled data, but sometimes there are abundant unlabeled data. We could touch on pre-training approaches (autoencoder pre-training, etc) as well as transfer +...

cgreene

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule) to see if the rule has already been proposed?** - [x] Yes Many machine learning application tolerate black-box models; however, research in...

tbrittoborges

Treat it as a statistical model

1

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule) to see if the rule has already been proposed?** - [x] Yes This rule is related to @ttriche's comments in #5. Because...

blengerich

Strive for balance between training, tuning, and testing datasets

1

Scientists should strive for balance in the training, tuning, and testing datasets to assure that different phenotypic groups are represented appropriately/similarly. This refers to the balanced proportion of different classes...

hugoaerts