𝐉𝐔𝐁𝐋𝐈𝐍𝐆𝐑𝐄𝐀𝐕 (𝐃)

Price respecting 21EMA and bouncing back from it 🧐

@PAlearner @Puretechnicals9 @AnandableAnand
@ArjunB9591 @harrie007 @Jitendra_stock @MaverickAmit01

#Thread The legend of Ekadash Mukhi Hanuman ji...

Mahadev himself narrated the story of Ekadash Mukhi Hanuman ji to Maa Parvati. Once a great monster named Kalkarmukh performed the severe penance of Brahma ji.

Pleased with the austerity of the demon, Brahma ji gave him a boon that the person who will have eleven Heads like you and who was born on the day of your birth, only he/she will be able to kill you. No one else will kill you.

After getting a boon from Brahma ji, Kalkarmukh created a ruckus in all three lok. He invaded Swarg and snatched all the rights of the Devtas and became himself the king of Swarg.

All Devtagan came to Shri Rama and asked him for help. Hearing the agony of the Devtagan, Shri Ram called his supreme devotee Hanuman ji and said, "Pawan Putra, Sankatmochan".

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.

AHOBILAM NARASIMHA SWAMY KSHETRAM: KURNOOL (AP)
#andhratemples

Ahobilam is the place where Prabhu appears in his fierce form, called Ugra Narasimha, who is Svayambhu (self-manifest).
Ahobilam is one of the 108 Divya Desams. It has 9 shrines for different forms of Narsimha.

Ahobilam was the exact place where Sri Narasimha appeared and tore apart Hiranyakashipu to save Prahlad. At that moment, all the Devas appeared and praised him as Ahobala (Aho is mighty and bala is strength). So the place came to be called Ahobilam.

Out of the 9 shrines, most famous is the Ahobila Narasimha Swamy where Prabhu is seen as Ugra Narasimha.
In another shrine, Prabhu appears as Malola Narasimha Swamy. Malola means beloved of Lakshmi. Here Prabhu is in peaceful mudra with his consort Ma ChenchuLakshmi.

Jwala Narasimha Swamy shrine is the actual spot where the fierce anger of Prabhu reached its culmination when he tore Hiranyakasipu.

Ugra Stambham is the pillar from which Narasimha appeared with such force that the entire hill split into two.

Remember: Just because an idea is old doesn't mean it's good.

Knowing whether old ideas are more likely to be good requires understanding whether conditions have changed in important ways.

Horse archery was an amazing method of warfare for over a thousand years...then people invented guns, and suddenly this great idea that had stood the test of time became obsolete.

Then again, when underlying conditions don't change much, tried-and-true approaches are probably better.

"Learning the lessons of history" usually just means assuming ergodicity and stationarity in an informal time-series model...

(end)