jacobian

Unnamed repository; edit this file 'description' to name the repository.
Log | Files | Refs | README

commit 54787847d8e9cf6fe1512ef6bb29478ce4b27f8b
parent 95ab74a318efd0dbf671b824e6597d0eb5565fdb
Author: David Freifeld <freifeld.david@gmail.com>
Date:   Fri, 31 Jul 2020 13:49:07 -0700

Added new figure + readme tweak

Diffstat:
Apictures/metrics.png | 0
Mreadme.md | 4++--
2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/pictures/metrics.png b/pictures/metrics.png Binary files differ. diff --git a/readme.md b/readme.md @@ -12,9 +12,9 @@ Jacobian is a work-in-progress machine learning library written in C++ designed ## Benchmark Info -One of the tradeoffs of Jacobian is that as of now it doesn't train nearly as close to perfection as other available libraries (with the benefit being the added speed. Here's a graph of Jacobian's loss over epochs on a simple task (banknote dataset with batch size 16) as compared to other libraries. +One of the tradeoffs of Jacobian is that as of now it doesn't train nearly as close to perfection as other available libraries and doesn't maximize accuracy as much (with the benefit being the added speed. Here's a graph of Jacobian's model metrics over epochs on a simple task (banknote dataset with batch size 16) as compared to other libraries. -![Loss vs. Epochs](./pictures/loss.png) +![Loss vs. Epochs](./pictures/metrics.png) Here's a runtime comparison for a simple example task (same as before) between Jacobian and some other popular ML libraries: