short_course/day_plan.md

In rdrr1990/kerasformula: A High-Level R Interface for Neural Nets

Plan for Day

Pete 8/16/2018

9-9:15 Meet & Greet

9:15-10 Lecture 1: Overview & Learning Goals

leads into Demo 1 ... walk through install (if need be); introduce data; demonstrate basic of kerasformula functionality

Lecture 1 link

10-10:30 Lab 1: 'hello kerasformula'

Participants answer quick questions in Lab1.md which highlight structure of input and output.

10:30-10:45 Break

10:45-11:15 Lecture 2: Key Elements of Neural Nets

Lecture 2 link

11:15-Noon Lab 2: Design your own Neural Net

Participants build their own neural net using their own data and answer short questions found in Lab2.md which prompts them to estimate several models, take notes on output, etc.

(Participants should have a sample of their own data in a data.frame which is clean enough to run a regression on. Alternatively, code will be provided to quickly construct such a data.frame too and which will be similar to the data used in the slides.)

Noon-1 Lunch

1-1:30 Lecture 3: Avoiding Overfitting with kerasformula

Lecture 3 link

1:30-2 Lab 3: Triage against overfitting

Complete Lab3.md

2-2:15 Break

2:15-3:00 Lecture 4: Text as Data with kerasformula

Data reduction of text counts/ranks via embedding with troll tweets as data...

Lecture 4 link

3:00-3:30 Lab 4: Congressional Text as Data

Participants complete text as data lab4.md with provided data (if latter more amendable to working with counts / ranks of text).

3:30-3:45 Break

3:45-4:15 Lecture 5: Advanced Neural Nets in Keras

Lecture 5 link

4:15-5 Lecture 6 + Discussion: Promises and Pitfalls of Neural Nets for Political Research

Lecture 6 link

rdrr1990/kerasformula documentation built on June 6, 2019, 8:02 a.m.