# Interview: Emrah Gultekin, Co-founder of Chooch

NTR is a software development company and, as such, we tend to hangout with people who are interested in technology. We travel to hotbeds of tech in other countries to attend events and conferences where we get to know representatives of startups and companies.

We thought you would enjoy meeting some of them, too, learn about their experiences and benefit from their insights as we have.

During a trip to Silicon Valley, NTR’s CRO Yana Kazantseva met with Emrah Gultekin, Co-founder and CEO of Chooch, an AI training platform for visual recognition, based in San Francisco.

# Share Our TOPs

International Programmers’ Day was last week; today we give a special shout-out to those programmers who developed the apps that allow companies to communicate easily and provide services to clients from around the world.

NTR Lab is one of those companies; we work remotely using multiple technologies to communicate and collaborate with companies in dozens of countries. We also connect with them in person during road trips taken specifically to meet them.

Today we would like to tell more about life of our software development company and present the most popular and interesting stuff happened recently. We prepared list post with our TOPs.

# Why Do Neural Networks Need An Activation Function?

by Computer Vision Department of NTRLab

Suppose we are given a set of distinct points P = {(xi, yi) ∈ ℝm ×ℝ}i=1,…,n which we regard as a set of test samples xi ∈ ℝm with known answers yi ∈ ℝ. To avoid non-compactness we may assume that P lie in some compact K, for example, K may be some polytope. Does there exist some continuous function in space of all C(K) continuous functions on K such that its graph is a good approximation for our set P in some sense?

From the approximation theory point of view, a neural network is a family of functions {Fθ, θ ∈ Θ} of some functional class. Each special neural network defines each own family of functions. Some of them might be equivalent in some sense. If we restrict ourselves to only MLP according to the above problem with only one intermediate layer consisting of N elements then the corresponding family of functions will be