From a59cc4f1af1a436b4237489ca2cd55066f5bb4e4 Mon Sep 17 00:00:00 2001 From: oscars47 Date: Thu, 4 Jul 2024 01:30:03 -0700 Subject: [PATCH] slight update to verbiage --- index.html | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/index.html b/index.html index 0a8823c..a8efa84 100644 --- a/index.html +++ b/index.html @@ -181,7 +181,7 @@

Bio

——————————————————

- I keep a blog on AI and consciousness with a really cool backend (see project description on this page), oscars47.github.io/math-zombies/, along with Professor Gizem Karaali and Kamden Baer.

+ I keep a blog on AI and consciousness with a cool backend (see project description on this page), oscars47.github.io/math-zombies/, along with Professor Gizem Karaali and Kamden Baer.

See also my poetry website, oscars47.github.io/garbage-collector/. @@ -223,7 +223,7 @@

Projects

Confusion matrices for 39 species discrimination on the Watkins Marine Mammals dataset. Top row is using an XGB model trained on extracted features, and the bottom is using a retrained ResNet-50. First column is validation dataset, second is test.

- OSCAR (named by Professor Weiqing Gu) is my first project at Dasion as as Machine Learning Engineer, of which I am senior personnel. OSCAR stands for Ocean Science Cutting-edge Anomaly Research, and the focus is developing an interpetable, differential geometric approach to real-time, energy efficient decision making in underwater autonomous vehicles. Applied for DoN 24.2 SBIR grant for Context Aware Datastream Preprocessor for Time-Sensitive Applications. Currently, I have tested on the Watkins Marine Mammal acoustic dataset, achieving 99.3% validation accuracy and 98.7% test accuracy on distinguishing 39 different classes of mammals on a max depth 5 50 esimtator model. In collaboration with researchers at MBARI (Monterey Bay Aquarium Research Institute) to extend this model to other kinds of data. + OSCAR (named by Professor Weiqing Gu) is my first project at Dasion as as Machine Learning Engineer, of which I am senior personnel / lead researcher. OSCAR stands for Ocean Science Cutting-edge Anomaly Research, and the focus is developing an interpetable, differential geometric approach to real-time, energy efficient decision making in underwater autonomous vehicles. Helped co-author a grant proposal and a patent application. Currently, I have tested on the Watkins Marine Mammal acoustic dataset, achieving 99.3% validation accuracy and 98.7% test accuracy on distinguishing 39 different classes of mammals on a max depth 5 50 esimtator eXtreme Gradient Boosting model. In collaboration with researchers at MBARI (Monterey Bay Aquarium Research Institute) to extend this model to other kinds of data.

@@ -440,7 +440,7 @@

December 2023

trabbit
Artistic representation of my trabbit algorithm.
-

Published a package with the function trabbit, a custom gradient-descent based optimization algorithm, available at pypi.org/project/oscars-toolbox/.

+

Published a package with the function trabbit, a custom gradient-descent based optimization algorithm, available at pypi.org/project/oscars-toolbox/ [have since added some helper functions for torch].

October 2023