Neural Nets from Scratch

Daniel Polites

2024-04-03

Chapter 1 Intro

This is a write-up of iRisk’s Spring 2024 project: Neural Nets from Scratch

---

The organization is:

2. Single-Layer NN Notes
   • intro notation & methodology for single-hidden layer neural network
3. Digit Model
   • GLMs on MNIST handwritten digits as an application intro
4. Multi-Layer NN Notes
   • intro notation & methodology for multi-hidden layer neural network
5. Multi-Layer NN Model
   • implementation of multi-layer neural network in R

1.0.1 Setup

knitr::opts_chunk$set(echo = TRUE)
set.seed(50)
library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.3.1

## Warning: package 'readr' was built under R version 4.3.1

## Warning: package 'forcats' was built under R version 4.3.1

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.2     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.2     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(keras)

## Warning: package 'keras' was built under R version 4.3.2

library(glmnet)

## Warning: package 'glmnet' was built under R version 4.3.2

## Loading required package: Matrix

## Warning: package 'Matrix' was built under R version 4.3.2

## 
## Attaching package: 'Matrix'
## 
## The following objects are masked from 'package:tidyr':
## 
##     expand, pack, unpack
## 
## Loaded glmnet 4.1-8