Core tech

At the heart of Our Technology is our
groundbreaking eXplainable AI (XAI) technology.

A first-of-its-kind XAI engine

Senfino’s XAI engine leverages decades of advanced research from the highest echelons of academia. The engine was built from the ground up in C++ and employs a novel approach to neuro-fuzzy and deep learning that provides for interpretability and explainability in a personalized, AI-assistant context.

Increased Accountability
Increased Trust
Increased Efficiency

From Black Box to Glass BoxAnd Why Does Explanaibility Matter?

Explainable AI serves to uncover the black box of AI and reveals the “why” behind complex data sets resulting in recommendations, offering humans an easily understandable explanation to machine-based results.


XAI offers explanation, which means humans don’t have to take answers at face value any longer. Explanations can come in many forms, be it text, visual, or graph.


Not all explanations are created alike. Humans come with their ability to interpret information, so for example a doctor would demand a different explanation for a diagnosis than a patient, who speaks in lay terms.


The ability to lift the lid and see what’s happening inside can have significant impact in curtailing algorithmic discrimination and bias.


In regulated industries with compliance scenarios, it’s imperative to use XAI technology in automation. The ability to look under the hood and see how decisions were made can prevent significant legal exposure.

Interested in Explainability Design?

From Deep Learning to Deep Reasoning with XAI

Most AI solutions in the market are based on a set of algorithms that fall into the Deep Learning subset. While Deep Learning
is great at pattern recognition and making predictions, it falls short when it comes to personalization, explainability, and
understanding causality. The underlying architecture of our Deep Reasoning XAI technology is fundamentally different as
compared to deep learning, often giving as much or even more accuracy than neural networks without its data hungry nature.

No more cold start
Less training
data needed
without latency

GDPR and other regulations require AI decisions to be
explainable, rendering all existing AI illegal and opening the
flood gates to XAI-based technology

Our XAI Research On the World Stage

Publication: A Content-Based Recommendation System Using Neuro-Fuzzy Approach

Senfino Content Based Recommendation System Using Neuro-Fuzzy Approach provides human machine interpretable explanation in an AI assistant context. Our Neuro-Fuzzy architecture delivers substantial performance improvements returning acutely accurate personalized content and recommendations based on individual behavior without relying on collaborative filtering (crowd sampling).

Publication: Towards Interpretability of the Movie Recommender Based on a Neuro-Fuzzy Approach

Senfino Fast Computing Framework for Convolutional Neural Networks (FCFCNN) embodies unique XAI architecture reducing processing overhead while accelerating forward signal flow. Neurons store reference pointers to corresponding regions of previous input propagating signal flow, eliminating the need to search for connections between layers. Additionally, reference points are batched along with feature maps in multi-feature input containers and treated as vectors, speeding calculations across CNN layers. In benchmark tests of image validation, FCFCNN performed twice as fast as the leading OverFeat CNN.

Our XAI engine applied in HealthCare


Optopol, formerly a division of Canon, has been creating ophthalmological equipment for the past three decades. They partnered with Senfino to integrate our XAI engine for diagnostics. Our integration couples machine vision with our XAI core technology to detect, diagnose, and explain very complex diagnoses. The results have been outstanding, even diagnosing better than human-based doctors.

According to PWC, XAI is one of the
top 10 hottest trends in AI in 2018

From Big Data Predictions to XAI Decision Augmentation

The more you understand a problem, the easier it is to solve. Big data offers tremendous opportunity to gain insights
from analytics but the vast majority of data assets aren’t harnessed or aren’t actionable. Senfino XAI offers greater,
more accurate insights from a broad frame of explainable data reference, including structured and unstructured
data of various types such as real world 3D images, Internet of Things, video, text, audio, financial and market data,
abstract topics, language patterns and behaviors. Whether that means individualized recommendations, contextually
aware personalized AI assistance, just-in-time communications, mission critical information or life critical process automation.

XAI news from the outside

An in-depth primer on XAI provided by our colleagues at PwC.

Artificial intelligence has a trust problem and DARPA knows it.

The NYTimes know that as AI becomes more powerful, the field’s researchers increasingly find themselves unable to account for what their algorithms know — or how they know it.

Harvard Business Review shows how opaque AI models can have unintended consequences and why certain levels of transparency are needed.

Get in touch

New York

The epicenter of Commercialization is where
Senfino XAI honed its craft of driving new,
value-creating ideas through client
organizations and into market.


Warsaw is home to the best digital design
and development talent – recently ranked a
Top 3 Market for progressive digital thinkers
and doers, worldwide.