Powered by


machine learning

Reinforcement Learning

This article describes simple hacks you can use to train a bot in a very complex environment on a regular notebook in a relatively short time using only reinforcement learning, without the need for huge computational clusters and professional players’ game records.

Read more >

Deltix Codeforces Summer Round

Welcome to the second installment of our rounds. We have prepared valuable trophies for participants and winners.

Read more >

WebGL Shaders And Other Ways to Make a Website Unusable

To make the deltix.io website memorable, we wanted to create something unique, something that would distinguish us from other corporate front pages. What we ended up with, is a website that would feature procedural graphics producing a smooth high-resolution render.

Read more >

TimeBase Joins FINOS Community

We are excited to announce that TimeBase Community Edition joined a FinTech Open-Source Foundation (FINOS) on the 14th of July.

Read more >

Log4j and Gflog Java Logging Libraries

This article will peek under the hood of Log4j and Gflog java logging libraries and see how they are different from the memory management perspective. We will find out how things are implemented to keep allocations of new objects as low as possible.

Read more >

Differential Machine Learning

This paper provides new neural network types research, which allows to significantly speed up fair price and risk evaluation for various Option contracts. Methods described in this research allow traders to recognize arbitrage opportunities faster than competitors and, thus generate profit.

Read more >

Deltix Codeforces Round

Welcome to the first installment of our rounds. We have prepared valuable trophies for participants and winners. Top 100 participants will also receive a competition t-shirt. Another 100 t-shirts will be distributed randomly between 100 participants outside of the top-100 and who have solved at least one problem and participated in rated Codeforces rounds before.

Read more >