peter frick (@peterlfrick) profile picture

peter frick

@peterlfrick
Joined March 2014
  • Tweets63
  • Following249
  • Followers30
10Media
Photo by peter frick (@peterlfrick)Photo by peter frick (@peterlfrick)Photo by peter frick (@peterlfrick)Photo by peter frick (@peterlfrick)Photo by peter frick (@peterlfrick)Photo by peter frick (@peterlfrick)Photo by peter frick (@peterlfrick)
ML performance is a subset of ML business value. Encoding business goals into the objective function of models boosts overall impact @MLconf #mlconf
Image from peter frick (@peterlfrick)
1
1
Interesting explanation of variational autoencoders as a generalization of LDA, and how that’s used to scale recommendations @MLconf #mlconf
Image from peter frick (@peterlfrick)
1
2
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)
Image from Cecile Janssens (@cecilejanssens)
41
638
128
2,071
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…
Image from Tai-Danae Bradley (@math3ma)
55
1,173
121
3,484
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
69
215
peter frick retweeted
Nathan Yau (@flowingdata) profile picture
Nathan Yau@flowingdata15 Jan 2019
Goodbye, mid-range shot. flowingdata.com/2019/01/15/g…
7
142
37
460
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…
Image from Allen Downey (@AllenDowney)
1
5
1
24
Congrats Parker!
This quoted post is unavailable.
Try viewing anyway · View on X
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

The State of AI/ML in Python

AI and Machine Learning have catapulted Python into the number one programming language. This same trend brought new frameworks, and new contributors w…

speakerdeck.com
2
50
1
113
Clicked for the title, stayed for the memes
This quoted post is unavailable.
Try viewing anyway · View on X
peter frick retweeted
Kaggle (@kaggle) profile picture
Kaggle
@kaggle21 Aug 2018
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
Image from Kaggle (@kaggle)
3
469
25
1,137
How to Create an ARIMA Model for Time Series Forecasting in Python machinelearningmastery.com/a…
How to Create an ARIMA Model for Time Series Forecasting in Python - MachineLearningMastery.com

How to Create an ARIMA Model for Time Series Forecasting in Python - MachineLearningMastery.com

A popular and widely used statistical method for time series forecasting is the ARIMA model. ARIMA stands for AutoRegressive Integrated Moving Average and represents a cornerstone in time series...

machinelearningmastery.com
11
30
peter frick retweeted
Real Python (@realpython) profile picture
Real Python
@realpython4 Jun 2018
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…
Python Project Structure: How to Choose the Right Layout – Real Python

Python Project Structure: How to Choose the Right Layout – Real Python

Learn how to structure Python projects: pick between flat and src/ layouts, organize your code, and apply the patterns to CLI, web, and GUI apps.

realpython.com
4
110
8
327
how to train a neural network for text classification using keras frickp.github.io/neural-netw…
2
"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)
Image from Radim Řehůřek (@RadimRehurek)
86
2
216
"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
Image from Radim Řehůřek (@RadimRehurek)
3
75
3
221
virtual memory
Image from 🔎Julia Evans🔍 (@b0rk)
54
1,354
46
4,439
peter frick retweeted
Daren Willman (@darenw) profile picture
Daren Willman@darenw7 Apr 2018
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.
Image from Daren Willman (@darenw)
5
35
3
139
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
Image from Gael Varoquaux 🦋 (@GaelVaroquaux)
1
107
344
peter frick retweeted
Sasha Rush (@srush_nlp) profile picture
Sasha Rush
@srush_nlp4 Apr 2018
The Annotated Transformer: Line-by-Line PyTorch implementation of "Attention is All You Need" nlp.seas.harvard.edu/2018/04…
Image from Sasha Rush (@srush_nlp)
5
266
24
685
Load more