Deep Image Prior defies the idea that “deep learning only works in the context of massive datasets or models pretrained on such datasets”. This paper showed that some deep neural networks could be successfully trained on a single image without large datasets, the structure of the network itself could be preventing deep networks from overfitting.
This post presents a walk through of an object detection process applied to Audio/Video receiver back panel images. 1
Two transaction models dominate the blockchain world today - Account-based model where transactions are modeled as transfers happening from or to per-user accounts, and “unspent transaction output” or UTXO-based transactions. This post dives into the UTXO model, its design, execution and properties.
This is a short introduction to zero knowledge proofs (ZKP), along with some motivating examples. The aim of this post is to generate curiosity among the readers for this upcoming new area of research. After giving the readers an intution of what zero knowledge proofs are, In the next posts I would then get into some technical deep dives to show how ZKP is used in the wild.
Sharing a small page I cooked up to help people explore transformations - both the linear and the non-linear kind by drawing pictures and modifying them using transformations. This hack is in the spirit of the theme of this year’s Infinity festival at Pramati - where we have “Engaging the senses” as a theme. So, engage your senses to grasp the math of transformations.
Diffie–Hellman key exchange (DH) is a method of securely exchanging cryptographic keys over a public channel and was one of the first public-key protocols as originally conceptualized by Ralph Merkle and named after Whitfield Diffie and Martin Hellman. DH is one of the earliest practical examples of public key exchange implemented within the field of cryptography.
In this post we would first explain how a Diffie Hellman key exchange works. Then we would dive deeper into the details of elliptic curves and its properties. Finally we would show how Elliptic Curves can be used for efficient key exchange.
Screening through hundreds of mail and prioritizing your work for the day is a difficult job. One kind of prioritization that is important is dealing with deadlines that are indicated in emails such as a slide deck or report due. The first step of calendarizing deadlines is to identify that a deadline is indeed present. We’ve tried to tackle this deadline tagging as an email classification problem using a Bayesian approach with the result being PMail. We also built an RNN based model which we compare with the Bayesian approach. We were able to show promising results with the approaches we took, which we detail in this post.