My current project is re-identifying individual manta rays (Mobula alfredi and Mobula birostris) by their distinct belly patterns … er… ventral markings.
Every night at two spots on the Big Island of Hawai’i where I live, dive boats shine bright lights that attract plankton. Most nights, the plankton in turn …
more ...The "attention" in ML is "what you should attend to," not "alertness." In the sentence "They crossed the <???> to get to the other bank." you need to "attend to" the <???> word to disambiguate "bank". If <???> is "street" then it's "bank" as in "financial institution" (most likely). If <???> is "river" then …
more ...If you have a large FastAI (v2) DataLoaders and you're trying to debug something at epoch-scale (such as a custom metric), an easy way to train on a small subset of your data is:
subset_size = 100 # Or whatever
selected_items = np.random.choice(dls.train_ds.items, subset_size …The Chinese Room is a 1980 thought experiment from the philosopher John Searle. The Wikipedia summarizes the setup:
more ...[S]uppose that artificial intelligence research has succeeded in constructing a computer that behaves as if it understands Chinese. It takes Chinese characters as input and, by following the instructions of a …
I just deleted my intermediate data and models for Kaggle’s Happywhale competition. I did terrible, never getting much above pure random guessing. Which was frustrating, because it’s a problem in Machine Learning that I’m very interested in (and want to do more work in).
Don’t join a team too quickly. Once you’re on a Kaggle team:
Unless you have a very good sense of what exactly your teammates are bringing to the competition, including their:
At the risk of saying, “Yeah, it’s in the docs,” this is what I did. I think the crucial thing is installed things in the proper order, so I would advise going step-by-step:
conda installed (brew install conda if not, I suppose)conda …Get the source code and data on Github
This demonstrates how you create a multistep AzureML pipeline using a series of PythonScriptStep objects.
In this case, the calculation is extremely trivial: predicting Iris species using scikit-learn's Gaussian Naive Bayes. This pipeline could be solved (very quickly) using this code:
import …One of my big weekend projects (for longer than I care to think) has been trying to create a pipeline for identifying individual whalesharks from photos. The project had kind of grown moribund as I repeatedly failed to get any decent level of recognition despite using what I thought was …
more ...OMG I can't believe I missed this competition. It's exactly in line with my whaleshark identification project.
https://www.kaggle.com/c/humpback-whale-identification
Here's a baby humpback whale that swam up to the boat a few weeks ago. In the second photo you can see it popped it's head up …
more ...