jF3mO5aXiu

It's also a wonderful example of leveraging and customizing the fastai framework in a deep & thoughtful way.

Here's the full set of blog posts diving in to this project:

https://t.co/jF3mO5aXiu

https://t.co/DrCJxxJRAy

https://t.co/GgatWxa9nM

https://t.co/U9Yp5IZpxt

More from Data science

Ryan J. Gallagher
@ryanjgallag

Tired of word clouds? Want to do better sentiment analysis? Not sure how to look at the words underneath your measures?

Our long overdue paper on generalized word shift graphs is finally here!
https://t.co/lIBXvbMJWX
https://t.co/vSL1REYT8V

So what are they?

1/n

If we have two texts, there are many ways we can compare them. Weighted averages are a particularly useful measure because they're flexible and interpretable

Proportions, Shannon entropy, the KLD, the JSD, and dictionary methods can all be written as weighted averages

2/n

But weighted avgs are also slippery. When we try to compress complex phenomena like happiness, surprise, divergence, or diversity into a single number, it can be unclear what we're measuring

If the measure goes up, what does that mean? Why did it do that? Can we trust it?

3/n

Very often, that's the end of the line and we're left with an uneasy feeling in the pit of our stomach that our weighted avg is actually picking up a data artifact or some other unintended peculiarity

Word shift graphs help us address those concerns

4/n

First, word shifts look under the hood of weighted averages to see what's going on

All weighted averages are a sum of contributions from individual words. We can pull out those words, and rank which ones contribute the most to the difference between two texts

5/n

Greg Yang
@TheGregYang

1/ A ∞-wide NN of *any architecture* is a Gaussian process (GP) at init. The NN in fact evolves linearly in function space under SGD, so is a GP at *any time* during training. https://t.co/v1b6kndqCk With Tensor Programs, we can calculate this time-evolving GP w/o trainin any NN

2/ In this gif, narrow relu networks have high probability of initializing near the 0 function (because of relu) and getting stuck. This causes the function distribution to become multi-modal over time. However, for wide relu networks this is not an issue.

3/ This time-evolving GP depends on two kernels: the kernel describing the GP at init, and the kernel describing the linear evolution of this GP. The former is the NNGP kernel, and the latter is the Neural Tangent Kernel (NTK).

4/ Once we have these two kernels, we can derive the GP mean and covariance at any time t via straightforward linear algebra.

5/ So it remains to calculate the NNGP kernel and NT kernel for any given architecture. The first is described in https://t.co/cFWfNC5ALC and in this thread

$Sunrit Jana \U0001f680$

Sunrit Jana 🚀
@JanaSunrise

Pandas is an amazing data analysis and manipulation library for python, Really popular when working with ML, Data science or more.

It has a robust data structure, Dataframe for manipulation and analyzing data.

Here's some tips to help you work better with pandas. Let's go! ↓

If you're not aware about what a Dataframe is, It's an optimized data structure for loading data, analysing it, manipulating data in it, and Mostly gathering insights.

It uses Cython backend which transpiles into C for optimized code.

Here's how a dataframe looks like,

Before we start, You need to ensure, you have pandas installed. If you don't, Do that before moving ahead!

Here are the tips, Let's go!

1/ Convert PD series to Dataframe

We all have struggled, when we deal with pandas series. It's always easier to work with Dataframes, rather than series. Here is how you can convert series to dataframe easily.

2/ How to create dummy Dataframe for testing

We always need dataframes for testing and analysing normally, if we do not have data ready. Here is how you can use Pandas API to generate different types of data.

Maria Khalusova
@mariaKhalusova

To my JVM friends looking to explore Machine Learning techniques - you don’t necessarily have to learn Python to do that. There are libraries you can use from the comfort of your JVM environment. 🧵👇

https://t.co/EwwOzgfDca : Deep Learning framework in Java that supports the whole cycle: from data loading and preprocessing to building and tuning a variety deep learning networks.

https://t.co/J4qMzPAZ6u Framework for defining machine learning models, including feature generation and transformations, as directed acyclic graphs (DAGs).

https://t.co/9IgKkSxPCq a machine learning library in Java that provides multi-class classification, regression, clustering, anomaly detection and multi-label classification.

https://t.co/EAqn2YngIE : TensorFlow Java API (experimental)

elvis
@omarsar0

I have always emphasized on the importance of mathematics in machine learning.

Here is a compilation of resources (books, videos & papers) to get you going.

(Note: It's not an exhaustive list but I have carefully curated it based on my experience and observations)

📘 Mathematics for Machine Learning

by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong

https://t.co/zSpp67kJSg

Note: this is probably the place you want to start. Start slowly and work on some examples. Pay close attention to the notation and get comfortable with it.

📘 Pattern Recognition and Machine Learning

by Christopher Bishop

Note: Prior to the book above, this is the book that I used to recommend to get familiar with math-related concepts used in machine learning. A very solid book in my view and it's heavily referenced in academia.

📘 The Elements of Statistical Learning

by Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie

Mote: machine learning deals with data and in turn uncertainty which is what statistics teach. Get comfortable with topics like estimators, statistical significance,...

📘 Probability Theory: The Logic of Science

by E. T. Jaynes

Note: In machine learning, we are interested in building probabilistic models and thus you will come across concepts from probability theory like conditional probability and different probability distributions.

And here they are...

THE WINNERS OF THE 24 HOUR STARTUP CHALLENGE

Remember, this money is just fun. If you launched a product (or even attempted a launch) - you did something worth MUCH more than $1,000.

#24hrstartup

The winners 👇

#10

Lattes For Change - Skip a latte and save a life.

https://t.co/M75RAirZzs

@frantzfries built a platform where you can see how skipping your morning latte could do for the world.

A great product for a great cause.

Congrats Chris on winning $250!

#9

Instaland - Create amazing landing pages for your followers.

https://t.co/5KkveJTAsy

A team project! @bpmct and @BaileyPumfleet built a tool for social media influencers to create simple "swipe up" landing pages for followers.

Really impressive for 24 hours. Congrats!

#8

SayHenlo - Chat without distractions

https://t.co/og0B7gmkW6

Built by @DaltonEdwards, it's a platform for combatting conversation overload. This product was also coded exclusively from an iPad 😲

Dalton is a beast. I'm so excited he placed in the top 10.

#7

CoderStory - Learn to code from developers across the globe!

https://t.co/86Ay6nF4AY

Built by @jesswallaceuk, the project is focused on highlighting the experience of developers and people learning to code.

I wish this existed when I learned to code! Congrats on $250!!