Learning with distributional inverters

no code implementations • 23 Dec 2021 • Eric Binnendyk, Marco Carmosino, Antonina Kolokolova, Ramyaa Ramyaa, Manuel Sabin

- If there is a strongly useful natural property in the sense of Razborov & Rudich 1997 -- an efficient algorithm that can distinguish between random strings and strings of non-trivial circuit complexity -- then general polynomial-sized Boolean circuits are learnable over any efficiently samplable distribution in randomized polynomial time, given membership queries to the target function

GANs & Reels: Creating Irish Music using a Generative Adversarial Network

no code implementations • 29 Oct 2020 • Antonina Kolokolova, Mitchell Billard, Robert Bishop, Moustafa Elsisy, Zachary Northcott, Laura Graves, Vineel Nagisetty, Heather Patey

In this paper we present a method for algorithmic melody generation using a generative adversarial network without recurrent components.

Generative Adversarial Network Music Generation

Non-Sequential Melody Generation

no code implementations • ICLR 2020 • Mitchell Billard, Robert Bishop, Moustafa Elsisy, Laura Graves, Antonina Kolokolova, Vineel Nagisetty, Zachary Northcott, Heather Patey

In this paper we present a method for algorithmic melody generation using a generative adversarial network without recurrent components.

Generative Adversarial Network Music Generation

Approximating solution structure of the Weighted Sentence Alignment problem

no code implementations • 8 Sep 2014 • Antonina Kolokolova, Renesa Nizamee

We study the complexity of approximating solution structure of the bijective weighted sentence alignment problem of DeNero and Klein (2008).

Sentence