How we came to be Spatialist.
Where it all started.
Spatialist is bridging the gap between virtual and physical reality. At Spatialist we are building the SaaS Content Management System for Brands and Companies entering the Spatial Web.
Like all good companies, we started with an idea; how do we best merge the digital and physical worlds? As a team we set out to answer that question, and along that path discovered there an approach, and a method that works.
We're pre-launch and focused on the product engineering phase, and looking for curious engineers to join and help build the next internet: the Spatial Web. We are a Studio-Based, remote-friendly company founded by an enthusiastic team of industry veterans and professionals.
At Spatialist, we are constantly striving to develop new and innovative ways to help people better understand their daily lives through the spatial data that our AI agents collect. Our ultimate goal is to provide individuals with the insights they need to make more informed decisions and improve their quality of life.
Our three current goals:
To provide people with an understanding of their daily lives through AI agents who spatialize in the environment.
To make agents more intelligent by spatializing them in the environment to better understand people's daily life.
A mission is to empower people with the ability to understand and control their environment through artificial intelligence.
The Science and Research of Ai Design.
Everyone has an external view of themselves, and we strive to merge this into an AI Agent, or an "Ai" and build a system that commercial produces high-quality, process driven, updateable and extremely deep, Expert Ai models. We look for information and data that is not on the internet and thus outside the knowledge Base of Chat GPT, or other Large Language Models. What we are looking at is Expert Language Models, and how to apply them to vertical businesses and specific value propositions within existing business models. Our research needs to continue the deep dive into interface and interactions and extension to this concepts will be to add to, and manage content production quality, all as part of our studio services.
This method of product engineering, a process driven continue improvement, version controlled and platform architected approach allows for our team to supervise the iteration of Machine Learning & model generation, and mix the blending, attribution, enrichment, and enhansments all within a UI enviroment build to support ongoing module, and service additions. By engineering a platform appoach to feature and function development, we control software availability through versions, and as needed release updates, add functionality, or develop entire new AI, spatial, and ambient value to our customers, and to theirs.
As a company we strive to gain SCO and humanize the core of all Ai: DATA. We build Expert Ai Machine Learning models to support broad applications of off-internet data. This starts as a service, to individual experts, luminaires, HNWI, support teams, family member and more.
Our approach to start with medium size corpus data sets, so people with a large, but not very large, data set. We prefer mixed media, and personal interviews. We aim to round-out all Expert AI engineering with Avatar development and deep-work on the personalization of each AI-Agent. This is a personal representation of a individuals knowledge, and where possible we work deeply and intensly with the human to best engineer this personal tool and interface.
We aim to support a large scale, yet individual conversion of data components to materials, and for the AI-Agent to interact with people, other AI-Agents, and output, verification, and decision leadership.
Building the future, the time is now.
Spatialist is a company that specializes in creating innovative Commercial Process Driven Ai. WE specialize again in using this Ai for use cases, such as Ai in mixed reality experiences using modular content innovations and commerce payment solutions. We continuously seeks new ways to innovate and grow in the field of Expert Ai, Spatial content and commerce, and deep-tech of Ambient Intelligence.
We aim to develop a true partnership where we take an equity state, in either your existing company or a separate second company developing this specific integration. After doing research anddeveloping a belief in substantial sustained economic potential in this method, it is our prefferend engineering and engagment model.
We understand that some technologies are going to require a continuous amount of effort to stay on top, and stay out front. By partnering with us, we centrally engineer this technology and distribute it across all our verticals, ensuring quick updates and support, while pressing innovation towards the extreme potential of the moemnt: teh AI Moment.
Ai, Spatial and Ambient are a gold rush. We sell shovels, axes and supplies to those who wish to find gold. Lets have a talk.
Spatial Ai explain-ability
Spatial.AI is artificial intelligence that allows humans to understand the results and decision-making processes of the model or system. Right now we're experiment with model applications; here are a few current models we use:
📚SHAP (SHapley Additive exPlanations)
SHAP is a model agnostic and works by breaking down the contribution of each feature and attributing a score to each feature.
📚 LIME (Local Interpretable Model-agnostic Explanations)
LIME is another model agnostic method that works by approximating the behavior of the model locally around a specific prediction.
Eli5 is a library for debugging and explaining classifiers. It provides feature importance scores, as well as "reason codes" for scikit-learn, Keras, xgboost, LightGBM, CatBoost.
Shapash is a Python library which aims to make machine learning interpretable and understandable to everyone. Shapash provides several types of visualization with explicit labels.
Anchors is a method for generating human-interpretable rules that can be used to explain the predictions of a machine learning model.
📚 XAI (eXplainable AI)
XAI is a library for explaining and visualizing the predictions of machine learning models including feature importance scores, decision trees, and rule-based explanations.
BreakDown is a tool that can be used to explain the predictions of linear models. It works by decomposing the model's output into the contribution of each input feature.
interpret-text is a library for explaining the predictions of natural language processing models.
📚 iml (Interpretable Machine Learning)
iml currently contains the interface and IO code from the Shap project, and it will potentially also do the same for the Lime project.
📚 aix360 (AI Explainability 360)
aix360 includes a comprehensive set of algorithms that cover different dimensions
OmniXAI (short for Omni eXplainable AI), addresses several problems with interpreting judgments produced by machine learning models in practice.