Building a recommendation engine? Microsoft has open sourced a collection of Jupyter Notebooks detailing best practices with machine learning and deep learning: https://t.co/fch69KHfiL
— David Smith (@revodavid) February 14, 2019
Building a recommendation engine? Microsoft has open sourced a collection of Jupyter Notebooks detailing best practices with machine learning and deep learning: https://t.co/fch69KHfiL
— David Smith (@revodavid) February 14, 2019
TPUs in Google Colaboratory, now with less boilerplate code. See the Keras TPU sample here: https://t.co/RIpkluc09d
— Martin Görner (@martin_gorner) February 13, 2019
google.colab.auth.authenticate_user() to propagate your credentials to the backend and the TPU. TPUClusterResolver() to find your TPU. That's it!
Effective TensorFlow 2.0: A Guide for Best Practices and What’s Changed.
— TensorFlow (@TensorFlow) February 13, 2019
Read more here → https://t.co/XcDDPW1xX5 pic.twitter.com/XeHpAsgjdM
Matthews Correlation Coefficient https://t.co/eZ2bbpDzwV pic.twitter.com/VMY6Vz43tm
— Chris Albon (@chrisalbon) February 13, 2019
Whether you are a beginner or not, if you are looking for a short and accessible book that covers a huge range of Machine Learning topics concisely (without sacrificing rigor or shying away from math equations), then read Andriy Burkov's excellent book: https://t.co/KKi9HPkqeX 👍
— Aurélien Geron (@aureliengeron) February 13, 2019
this poster is like a SUPER EXTRA COMPRESSED version of the "Bite Size Networking" zine I'm working on: the goal of that zine is to teach you the basics of lots of useful tools quickly ❤ https://t.co/MWtsVgjgKl
— 🔎Julia Evans🔍 (@b0rk) February 13, 2019
My favorite questions when interviewing data scientists are about ML explainability. ML explainability is so useful, but it isn't as widely known as it should be.
— Dan Becker (@dan_s_becker) February 12, 2019
Kaggle has a free micro-course teaching the key ideas in ML explainability. https://t.co/MkEXI4NujO
So much to learn about #machinelearning & #artificialintelligence on #pydata videos, including:
— PyData (@PyData) February 12, 2019
"Data versioning in machine learning projects" by Dmitry Petrov — how to solve the issue of discrepancy between code & data files https://t.co/4B317wMMnq
Don't forget to subscribe!
A new summary of XLM - a new model that upgrades BERT to achieve SOTA results in cross-lingual classification and translation tasks. https://t.co/lNd2UeuVPe
— Rani Horev (@HorevRani) February 11, 2019
Great paper by @alex_conneau & @GuillaumeLample from @facebookai
What Serverless Computing Should Become 🆕 must-read paper from @ucbrise outlines current state of serverless computing & lists research challenges in five areas: abstractions, systems, networking, security, and architecture https://t.co/4l18g9WCht pic.twitter.com/tW8rLLFVq2
— Ben Lorica 罗瑞卡 (@bigdata) February 10, 2019
https://t.co/aGmzxXL6Kv is a 10-week course that starts tomorrow. It was created with input from a bunch of Kaggle Grandmasters. Starts with manipulating data using Pandas. covers feature engineering, time series forecasting and training using GBMs.
— Anthony Goldbloom (@antgoldbloom) February 10, 2019
ethtool pic.twitter.com/EjAZHfo7Pt
— 🔎Julia Evans🔍 (@b0rk) February 10, 2019