Our new AI system learned speech recognition in English with *zero* speech to text training data: researchers just gave it lots of audio, and it figured out what the words were. But it goes way beyond that - it learned Swahili too!

Since many asked - we open sourced this work for all to use:

Today we are announcing our work on building speech recognition models without any labeled data! wav2vec-U rivals some of the best supervised systems from only two years ago.

Paper: https://t.co/cYzF9MGu56
Blog: https://t.co/iiGmgdnCiV
Code:

This shows how completely unsupervised speech recognition with wav2vec-U compares to the best supervised systems on the Librispeech benchmark over the past few years.

Here is how it works:

It also works in languages other than English, see the Swahili demo below. So far we tried it on Kyrgyz, Tatar, German, Dutch, French, Spanish, Portuguese, Italian.

A playlist of 30 lectures on mathematical writing by Donald Knuth (and guests). From 1987, but good writing is timeless. Definitely worth watching if you want to level-up your technical writing! Credits to @ayush_sekhari for the pointer.

The 5 Keys To Eliminate The Dad Bod

// THREAD //

#1: Protein 🥩

- protein is the most satiating macro
- protein has the highest thermic effect
- protein is the building block of muscle

Protein will allow you to pack on muscle AND make it easier to lose fat.

Eat more protein.

#2: Resistance Training 🏋️‍♂️

In order to grow muscle, you need to perform resistance training.

As a result, you will

- burn more calories because of the workouts
- have a higher metabolism with more muscle mass

#3: Meal Timing ⏰

When do you tend to be the most hungry?

Push the bulk of your calories into that time period.

This will set you up for sustainable success.

#4: High Volume Foods 🍉

Hunger is the enemy of fat loss success.

In order to combat hunger, we want to eat as many high-volume foods as possible.

- Fruits
- Veggies
- Popcorn
- Potatoes

This is Karma. Karma is not a machine learning classifier 🐕‍🦺

Karma is a real dog trained to detect drugs. However, he would fail the simplest tests we apply in ML...

Let me take you through this story from the eyes of an ML engineer.

https://t.co/WAXRUlTvSI

Thread 🧵

Story TLDR 🔖

The story is about police dogs trained to sniff drugs. The problem is that the dogs often signal drugs even if there are none. Then innocent people land in jail for days.

The cops even joke about the “probable cause on four legs”.

Let's see why is that 👇

1. Sampling Bias 🤏

Drugs were found in 64% of the cars Karma identified, which was praised by the police as very good. In the end, most people don't carry drugs in their cars, so 64% seems solid.

There was a sampling problem though... 👇

The cars were not sampled at random! The police only did the sniff test if there was a serious suspicion that something is wrong.

The chance there are drugs in the car is much higher in this case!

2. Evaluation Metrics 🔍

The police referred to a 2014 study from Poland measuring the efficacy of sniffer dogs. The problem was that every test actually contained drugs!

This means there was no chance to measure false positives from the dogs! Only recall, not precision 🤦‍♂️

@CSProfKGD Day #17 Google says "Pay Attention to MLPs"

Python Data Science Handbook.

An excellent book for those seeking an introduction to data science and machine learning.

Chapters have been converted to publicly available Colab notebooks.

Covers:
- NumPy
- Pandas
- Matplotlib
- ML algorithms

https://t.co/KjBpsDhDDJ

A surprising situation.

A machine learning model predicting 3 classes ends up with these results:

• Class A: 90% accuracy
• Class B: 80% accuracy
• Class C: 70% accuracy

Class C seems to be the worst-performing.

But you know already that I'll say it isn't. ↓

Here is the correct answer: We don't know yet which class is the worst.

This is important to understand, so keep reading.

Many people make this same mistake every day and try to fix things that ain't broken.

We are missing something, so let's go and get it.

How about if we ask a friend to look at the dataset manually?

Let's say these are the results of our friend doing the job:

• Class A: 95% accuracy
• Class B: 100% accuracy
• Class C: 71% accuracy

Do you see what just happened?

The model is actually really accurate when predicting Class C! 70% versus 71% when done by a human.

Class B, however, is a disaster: 80% versus 100% when done manually.

Class B seems to be the worse performing class!

The work that our friend did is called a "baseline."

Without having it, it's hard to determine how good are the results of a model.

I've seen tons of money down a drain just because teams didn't create a baseline beforehand.

But now, that won't happen to you 😉.

Some of the most amazing applications of machine learning will probably come from folks working on brain-computer interface (BCI).

Check out this new paper discussing high-performance brain-to-text communication via handwriting.

Future of programming?

https://t.co/I5DUnE4vpy

I learned enough AI/ML in 12 months to change my life forever.

You can do the same, and it all starts with a killer process to learn new things.

You can steal my approach. Every detail on the latest issue of my newsletter: https://t.co/9gaenLByFb.

Make it work for you.

My recommendation to start learning how to deal with structured data: Kaggle's Pandas Tutorial.

• Creating, Reading, Writing
• Indexing, Selecting, Assigning
• Summary Functions, Maps
• Grouping, Sorting
• Data Types, Missing Values
• Renaming, Combining

100% Python 🐍.

I just interviewed the man who invented Amazon Prime.

He started a business worth $40 billion today and served on Amazon's board for 15 yrs.

Here are lessons from Bing Gordon that'll save you years of mistakes:

When you have a business idea, take action now before it dies.

• Write 1 paragraph about the idea

• Write a 4 slide business plan

• Write your 1st line of code

When you start a job, ask your boss 2 questions:

1) Who is the best boss you've ever had and what does that mean for me?

2) What does top 10% performance look like?

Hold yourself accountable for high achievement.

If you're a cab driver, drive the most miles

if you're a fisherman, get on the best boat.

How to succeed

• Be a learning machine.
• Find a way to maintain high energy