https://t.co/5Rdn85mvPJ

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.

Ｇａｕ Ｍａｔａ Ｉｎ Ｖｅｄｉｃ
Ｃｕｌｔｕｒｅ

It is said that the one who bears the dust thrown from the hoof of Gaumata on his head, as if taking a bath in the water of the teerth sthalam and getting rid of all sins.

Ved and all other Hindu scriptures venerate the cow. The Vedic dictionary, Nighantu, gives amongst other synonyms of 'Gau' [ or cow] the words 'Aghnya', 'Ahi', and 'Aditi'.

Yaska the vedic decoder and commentator on Nighantu, defines these as-

Aghnya —— the one that ought not to be killed
Ahi —— the one that must not be slaughtered.
Aditi —— the one that ought not to be cut into pieces.

These three names of cow signify that this is an animal which should not to be put to tortures. These words appear frequently throughout the Veda in context of the cow.

But in due course the falsehood of killing cows spread far and wide and they became even more deep rooted when western scholars with their half baked knowledge of Sanskrit transliterated these interpretations of commentaries of Sayanacharya ,

WHY BABUR NEVER TRIED TO ATTACK SRI KRISHNADEVARAYA ?

A🧵u must read

It is very well known that Babur considered Krishna Dev Raya as the strongest ruler of the entire subcontinent, and Vijayanagar empire the strongest during that time in India.

1/10

The Vijayanagar empire reached its peak during 1509-1529 around the reign of Krishna Dev Raya.

Vijayanagar’s famed elephant brigade 👇

2/10

At his command there were over 50000 elite troops with a regiment of Portuguese gunners and 3200 cavalry with 600 elephants.

3/10

Along with that more than four hundred thousand ( four lakh) peasant levies and irregular military made this empire one of the largest in all of South Asia.

A typical Vijayanagar levie soldier 👇

4/10

During Baburs invasion, Krishna Dev Raya ruled supreme in all of deccan.

In fact, in an all our brawl, Krisha Dev Raya will beat Babur fair and square.

Babur could muster at max 50000 troops with 50 canons.

While Krishna Dev Raya had these numbers in Hampi alone

5/10