When you feed dogs you pacify your Ketu.

The barking noise (past memories) which was making it difficult for you to listen to your intuition get reduced.

Serve dogs, you will start to feel less traumatised and be able to hear the messages from your soul better.

Tried & Tested.

Important paper from Google on large batch optimization. They do impressively careful experiments measuring # iterations needed to achieve target validation error at various batch sizes. The main "surprise" is the lack of surprises. [thread]

https://t.co/7QIx5CFdfJ

The paper is a good example of lots of elements of good experimental design. They validate their metric by showing lots of variants give consistent results. They tune hyperparamters separately for each condition, check that optimum isn't at the endpoints, and measure sensitivity.

They have separate experiments where the hold fixed # iterations and # epochs, which (as they explain) measure very different things. They avoid confounds, such as batch norm's artificial dependence between batch size and regularization strength.

When the experiments are done carefully enough, the results are remarkably consistent between different datasets and architectures. Qualitatively, MNIST behaves just like ImageNet.

Importantly, they don't find any evidence for a "sharp/flat optima" effect whereby better optimization leads to worse final results. They have a good discussion of experimental artifacts/confounds in past papers where such effects were reported.

Can we control the output of neural generation systems?
Can we build a better chatbot using this control?
And what makes a good conversation anyway?

Check out the blog post for our NAACL paper:

https://t.co/UAAUxSeA0L

#AI #NLProc #DeepLearning #ConversationalAI @facebookai

This post got a little delayed since the paper's publication, but the intervening time has given me an opportunity to reflect.

So this post has some extra thoughts regarding more recent NLG developments - e.g., pretrained models like GPT(2), and the suitability of beam search.

The 2018 State of JavaScript survey is out. They got 20,000 responses and have some delicious, delicious data. I'mma thread in some highlights:

First up: JavaScript flavors. There's TypeScript at 47% adoption, a tad higher than npm's own survey results (which said 46%). npm's survey is coming up again soon and will ask about TypeScript in a lot more detail.

I really, *really* like SoJ's "would not use again" question, which lets people who've abandoned a tech self-identify. This is noticeable in the graph above with Flow users -- 41% of people who've used Flow say they wouldn't use it again.

Now JavaScript frameworks. It's been a full year since npm's survey, so these numbers differ from ours in the directions I expected:
React 65% (vs. 60%)
Vue 29% (vs. 24%)
Ember 5% (vs 4%, I was expecting a bigger rise)

But there's a shocker in here: Angular.

npm's survey had Angular at 40% last year and SoJ has it at either:
- 58% (if you include those who don't want to use it again)
- 24% (if you count only those who like it)
Since npm's question didn't ask if they intend to *continue* using it I think that might explain this.

🌺श्री गरुड़ पुराण - संक्षिप्त वर्णन🌺

हिन्दु धर्म के 18 पुराणों में से एक गरुड़ पुराण का हिन्दु धर्म में बड़ा महत्व है। गरुड़ पुराण में मृत्यु के बाद सद्गती की व्याख्या मिलती है। इस पुराण के अधिष्ठातृ देव भगवान विष्णु हैं, इसलिए ये वैष्णव पुराण है।

गरुड़ पुराण के अनुसार हमारे कर्मों का फल हमें हमारे जीवन-काल में तो मिलता ही है परंतु मृत्यु के बाद भी अच्छे बुरे कार्यों का उनके अनुसार फल मिलता है। इस कारण इस पुराण में निहित ज्ञान को प्राप्त करने के लिए घर के किसी सदस्य की मृत्यु के बाद का समय निर्धारित किया गया है...

..ताकि उस समय हम जीवन-मरण से जुड़े सभी सत्य जान सकें और मृत्यु के कारण बिछडने वाले सदस्य का दुख कम हो सके।
गरुड़ पुराण में विष्णु की भक्ति व अवतारों का विस्तार से उसी प्रकार वर्णन मिलता है जिस प्रकार भगवत पुराण में।आरम्भ में मनु से सृष्टि की उत्पत्ति,ध्रुव चरित्र की कथा मिलती है।

तदुपरांत सुर्य व चंद्र ग्रहों के मंत्र, शिव-पार्वती मंत्र,इन्द्र सम्बंधित मंत्र,सरस्वती मंत्र और नौ शक्तियों के बारे में विस्तार से बताया गया है।
इस पुराण में उन्नीस हज़ार श्लोक बताए जाते हैं और इसे दो भागों में कहा जाता है।
प्रथम भाग में विष्णुभक्ति और पूजा विधियों का उल्लेख है।

मृत्यु के उपरांत गरुड़ पुराण के श्रवण का प्रावधान है ।
पुराण के द्वितीय भाग में 'प्रेतकल्प' का विस्तार से वर्णन और नरकों में जीव के पड़ने का वृत्तांत मिलता है। मरने के बाद मनुष्य की क्या गति होती है, उसका किस प्रकार की योनियों में जन्म होता है, प्रेत योनि से मुक्ति के उपाय...