Hello! Welcome to

BitShots

Making paper abstracts readable!

20
2021 February

Hardcoded Attention

The transformer architecture is simply composed of stacked linear layers through which data is passing in a unique manner. The attention module consist of three separate neural nets...

Read more

20
2020 September

RFID Tattoo

UbiComp 2020, an A* conference on Ubiquitous and Pervasive Wearable technologies ended with a beautiful surprise. Never in my wildest dreams, had I thought that...

Read more

15
2020 August

Image GPT

The language models have been the torchbearers of SOTA in NLP from the past three years, which honestly, in deep learning years is equivalent to a decade!...

Read more

12
2020 July

Adversarial Reprogramming of NN

Leonardo DiCaprio famously said in his Oscar speech, “The climate change is real!”. Looking at the compute used by recent DL papers, I would not be surprised if...

Read more

17
2020 June

ELECTRA

Recently ICLR 2020 concluded with its virtual conference and among the 687 papers that were present in the fabled conference, one particularly caught my eye, ELECTRA...

Read more

5
2020 May

Is Bigger the Better?

Last year, a debate sprang across the NLP community when Google released XLNet, a model that improved upon BERT on 20 tasks! But...

Read more

20
2020 April

RNN vs LSTM vs Transformer

With the advent of data science, NLP researchers started modelling languages to better understand the context of the sentences for different NLP tasks.

Read more

8
2020 April

How do a machine sees a text?

The relation of raw data with numbers may not be as intuitive as it seems.

Read more