Deep learning is a broad field of research with
the objective of creating artificial intelligence that is capable of
instructing itself to perform tasks rather than relying on algorithms. In
theory, this would allow AI to succeed at tasks that would be prohibitively
difficult, resource intensive, or time-consuming for a human developer to work
on. However, deep learning requires dedicated experts to oversee and develop
the AI, undermining some of the intent behind having AI that can self-teach. If
you need an expert on hand regardless, why do you need an AI capable of deep
learning? AWS and Microsoft seek to change that.
In October, AWS and Microsoft announced that
they were working together to create Gluon, an open-source deep learning
library. Gluon brings together training algorithms and neural network models,
critical components of deep learning. With these in place, developers at a wide
range of skill levels have access to the essentials of deep learning
development and can begin to make their own inroads.
The companies have stated that Gluon is
currently intended to assist with creating machine learning models for
cloud-based applications, mobile apps, and any dedicated devices that may need
AI. The crucial detail is that it is open-source, making any progress easier to
share and improve upon. If Gluon proves successful, it could represent a major
step forward not merely for Microsoft and AWS, but the entire development
This isn’t the first effort from these two
companies to improve AI. Indeed, Syncfusion has discussed Microsoft’s efforts
to work with AI and the open-source community several times before
when Microsoft unveiled
the Zo chatbot, open
sourced Powershell, and joined
the Linux Foundation.
But it does represent perhaps most clearly the intention to open
up AI development to a wider audience. With any luck, we’ll all benefit from
more and better AI as a result of initiatives like these. If you’re interested
in AI, be sure to check out Machine Learning Using C# Succinctly and Microsoft Bot Framework Succinctly.