This repository has been archived by the owner on Aug 27, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 20
Simple Perceptron example? #9
Labels
Comments
I was thinking this material would be part of week 4 - DIY neural nets (which is my theoretical deadline for a rewrite of this chapter), but I could cover / assign the first section on the perceptron earlier. |
@shiffman - excellent! That's great to hear. I think it makes sense to have it in week 4 unless it is too much to pack into 1 week. |
There is a lot to do this week so I'm not sure if a full discussion of the Perceptron fits. I wonder if it might work well to double back into some of the details next week when we look at a second round of examples with the DIY neural network. I got lost in tensors this weekend so didn't get to make major revisions to chapter 10 yet. I should at a minimum add some links to #39 |
shiffman
added a commit
that referenced
this issue
Sep 23, 2019
shiffman
added a commit
that referenced
this issue
Sep 23, 2019
* skeleton of week 4 README * moving and editing material from google doc syllabus * Update 04_diy_neural_network/README.md Co-Authored-By: Ellen Nickles <[email protected]> * Update 04_diy_neural_network/README.md Co-Authored-By: Ellen Nickles <[email protected]> * adding video tutorials, moving new ImageNet works The new ImageNet works suggested by @ellennickles are excellent. I am going to put them with the ImageNet materials from earlier weeks since they match with that material better (this week is about non-image data) and then highlight them in class. * adding Excavating AI work thanks to @ellennickles * while i'm at it, adding Humans of AI by @philippschmitt * adding wattenberg and viegas talk #29 * adding nature of code chapter 10 #9 * removing two articles to reduce load could consider adding these back in later or somewhere else, etc. The nature.com article includes a lot of sophisticated statistics and math concepts / notation so is likely be beyond the scope of this course. cc @lydiajessup * [How to Make A.I. That’s Good for People](https://www.nytimes.com/2018/03/07/opinion/artificial-intelligence-human.html) by Fei-Fei Li * [Estimating the success of re-identifications in incomplete datasets using generative models](https://www.nature.com/articles/s41467-019-10933-3) from nature.com * ready for merge, still lots of work to do
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
For me one of the "ah-ha" moments was seeing what is going on in a Perceptron. Seeing how simple "intelligence" can be was very helpful to demystify the idea of defining fitness.
The text was updated successfully, but these errors were encountered: