Himanshu Rawlani

ML engineer | Gym lover | Foodie | Writer | Speaker

[François Chollet @fchollet]

Announcement: my book Deep Learning with Python (2nd edition) has been released.

500 pages of code examples, theory, context, practical tips... If you want to really understand how deep learning works, why it matters, and how to use it, this is your book!
https://t.co/LvbEy5A0k8

[Eugene Yan @eugeneyan]

Many machine learning papers and tutorials start from labeled datasets. But what if we don't have labels? How do we collect them?

Here we discuss semi-supervised learning, active learning, and weak supervision to bootstrap labels for your ML system.

https://t.co/RvsgXCFlIK

[Radhika Gupta @iRadhikaGupta]

The first person invested 12,000. In the first six years.

The second person invested 74,000. After chilling for six years.

At the end, both are about the same.

The magic of being the early bird!

[Dhruv Toshniwal @dhruv_toshniwal]

13/n The mind, by its very nature, is unruly, untamed and wild. It loves to dwell in imaginary futures or live in the past. It detests the present moment.

Because when the mind is truly in the moment, it dies. It disappears. A state of no-mind.

[Aditya Sharma @aditya1601_]

If you get a hard time saving money,

💵 Think of the savings amount
~as~
💸 Money spent in buying FREEDOM💪 for your future

You'll become more interested in saving a good amount now, and live financially free just a few years later.
#PersonalFinanceUnder25

[Himanshu Rawlani @raw_himanshu]

I wish I had a third person view of my life. Since it's easy to point out flaws than to realize doing the same.

[Himanshu Rawlani @raw_himanshu]

This is how you make a Rangoli !!!

[Ted Gioia @tedgioia]

A visual demonstration of the power of sound to create order out of chaos.

[@jackbutcher @jackbutcher]

Work on things that keep working after you stop working.

[@jackbutcher @jackbutcher]

Publishing proof > sending resumes.

[Sanyam Bhutani @bhutanisanyam1]

If you're looking for the best resources to prepare for ML interviews in 2020,

Here's a wiki from the @fastdotai forums:

https://t.co/S1nBfgOfLA

Also, all contributions are welcomed!

[Kunal Shah @kunalb11]

Our coaching classes spoon feeding culture and copy paste xerox of notes has resulted in a entire with terrible research skills.

[Emmanuel Ameisen @mlpowered]

This is one of the main tricks I recommend when trying to improve current model performance.

Don't start with hyperparameter search, start by looking at individual examples with large losses, and most of the time you'll understand what feature your model is missing.

[Himanshu Rawlani @raw_himanshu]

@BeerBicepsGuy Hi Ranveer, I would recommend "AI for Everyone" course (designed for technical and non technical users) on Coursera by Andrew NG: https://t.co/NnaBhRp0N5

This course explains ML terminologies, what ML can and cannot do, project workflows, case studies, and limitations of AI.

[Himanshu Rawlani @raw_himanshu]

⭐New blogpost⭐: Hyperparameter tuning with Keras and Ray Tune

A practical tutorial on using HyperOpt’s Bayesian optimization with HyperBand scheduler to choose the best hyperparameters for machine learning models.

Check out the blog: https://t.co/6Yo7YB4Lq0

@raydistributed

[@jackbutcher @jackbutcher]

1/

"Compound interest is the eighth wonder of the world. He who understands it, earns it. He who doesn't, pays it." — Albert Einstein

It affects:

Your health
Your money
Your relationships
Your reputation
Your abilities

[Amit Chaudhary @amitness]

I recently discovered an approach to run VSCode on Google Colab directly.

With the setup, you can use the notebook and the IDE side-by-side.

https://t.co/AKnBXYEGYp

[Amit Chaudhary @amitness]

Wrote a short post along with a colab notebook showing how you can use MarianMT models in @huggingface for text data augmentation.

https://t.co/kOY6Wrm8ya

[Amit Chaudhary @amitness]

Amazing article from @eugeneyan describing developments in NLP from RNNs(1985) to Big Bird(2020).

Really helps get a bird's-eye view of this rapidly progressing field.

https://t.co/ZOgjinhHwb

[François Chollet @fchollet]

A thing I hear sometimes: "what if my loss doesn't match the signature loss = fn(y_true, y_pred)?"

This is not a requirement in Keras -- it's only the default setting. If you have a loss with multiple inputs/targets, here are your options, in order of preference: (a thread)

[François Chollet @fchollet]

We now have 44 high-quality, short code examples demonstrating common workflows at https://t.co/eE1hRBF8Gt

Most of them are contributed by the community. They cover computer vision, NLP, timeseries, audio, generative deep learning, RL...