|
|
|
|
Safety_Critical_Machine_Learning |
|
|
AMEN™ is the synthesis of all our research and all the technologies we
study and develop. It is ultimately the main goal and, at the same time, the
set of rules that guide the development process of the AI we
desire: Accountable, Measurable, Explainable.
When an AI-based system tells you the route you need to
make sure it is Accountable: Our research is specifically oriented to find technological methods
to map human responsibility in Artificial Intelligence processes, however
complex they may be. Measurable: Our research has always been committed to developing algorithms and
methods that allow us to measure the reliability of inference with
mathematically explainable and non-statistical methods. Measurability is the
fundamental characteristic of an automatic inferential process so that human
responsibilities can be mapped onto it. Explainable: The explainability of algorithms has always been a cornerstone of our
research. It is a characteristic that exists in synergy with measurability.
If an algorithm is explainable, it is also measurable, and vice versa. This
isn't just a slogan; it's a science based on rules and metrics that operate
in a multidimensional space. |
Our research for a sustainable and safety AI
|
|
|
General Synaptics Aerospace_and_Defence_Machine_Learning_Company VAT NUMBER:_IT02670700992 REA NUMBER: GE-503104 Email:_luca.marchese@synaptics.org |
|
|
|
Copyright© 2026 General Synaptics |
