peter frick retweeted
The area under the ROC curve (AUC) is so frequently criticized and misunderstood that I often wonder whether I am the metric’s only fan. Let me explain why how I see and value the AUC.
(thread)
peter frick retweeted
A nice fact I like: Every matrix corresponds to a graph, and so familiar things (e.g. matrix multiplication) have nice pictures! Another nice fact: joint probability distributions *also* correspond to graphs. They have telling pictures, too. New blog post! math3ma.com/blog/matrices-pr…
peter frick retweeted
A comprehensive overview and break-down of 14 NLP research paper highlights from 2018
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
peter frick retweeted
A recent paper in NEJM shows that children born in August are 30% more likely to be diagnosed with ADHD than children born in September, probably because they start school younger.
I reanalyzed the data using Bayesian logistic regression:
allendowney.com/blog/2018/12…
peter frick retweeted
Slides for my talk @py_bay about AI/ML and Python are located here: speakerdeck.com/teoliphant/m… #PyBay2018 #MachineLearning #Python @NumFOCUS @TensorFlow @PyTorch @ChainerOfficial @ApacheMXNet
peter frick retweeted
RT @afshinea 🔥Set of illustrated Machine Learning cheat sheets from Stanford's CS 229 class:
Deep Learning: stanford.io/2BsQ91Q
Supervised Learning: stanford.io/2nRlxxp
Unsupervised Learning: stanford.io/2MmP6FN
Tips and tricks: stanford.io/2MEHwFM
peter frick retweeted
How to Create an ARIMA Model for Time Series Forecasting in Python machinelearningmastery.com/a…
peter frick retweeted
One of the top questions we've been getting from new Python coders is "how should I structure my Python projects?"
With this tutorial, we want to give you a dependable Python application layout reference guide that you can refer to: realpython.com/python-applic…
peter frick retweeted
"Advances in Semantic Textual Similarity": @GoogleAI's new post on universal text embeddings: ai.googleblog.com/2018/05/ad…
Pre-trained 512 dim #Tensorflow model: tensorflow.org/hub/modules/g… (already available in @scaletext_ai)
peter frick retweeted
"Context is Everything: Finding Meaning Statistically in Semantic Spaces." A replacement of tf-idf that is actually better than tf-idf (finally?!)
arxiv.org/abs/1803.08493
peter frick retweeted
Just for fun... Here's how an outfield of all Buxton would compare to an outfield of all Pujols based on 2017 sprint speed. Each colored band is a second of hang time. outer band is 6 seconds, inner band 3.
peter frick retweeted
Variational autoencoders: best tutorial so far, with intuition _and_ formalism, deep learning _and_ probabilistic model point of view
jaan.io/what-is-variational-…
by @thejaan
peter frick retweeted
The Annotated Transformer: Line-by-Line PyTorch implementation of "Attention is All You Need"
nlp.seas.harvard.edu/2018/04…
peter frick retweeted
As of TensorFlow 1.7, with eager execution, you can use a Chainer-like API in tf.keras to create models with dynamic control flow. This should be especially useful for NLP researchers working with recursive models!
peter frick retweeted
Here are the slides from our talk. slideshare.net/justinbasilic…
peter frick retweeted
Slides for this presentation are available at:
docs.google.com/presentation…
If in doubt, tweet for clarification ^_^
peter frick retweeted
The reason for bioRxiv in one image xitter.cf/YongshengShi/status/97…
peter frick retweeted
"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling," Bai et al.: arxiv.org/abs/1803.01271
