Analytics Studio

AutoML Code Generation and Analysis Tools You Won’t Outgrow

Sophisticated Machine Learning Tools

SensiML Analytics Studio, the core of the SensiML software suite, uses your labeled datasets to rapidly generate efficient inference models using AutoML and an extensive library of edge optimized features and classifiers. Using cloud-based model search, Analytics Studio can transform your labeled raw data into high performance edge algorithms in minutes or hours, not weeks or months as with hand-coding.

Whether a seasoned ML expert or just learning the basics of data science, Analytics Studio offers a tool that can substantially increase your embedded algorithm development productivity. It incorporates UI driven, constraint-based model generation, rich graphical results visualization, and extensive model testing and tuning.


Efficient AutoML Code Generation for Edge Sensing

Analytics Studio uses AutoML to tackle the complexities of machine learning algorithm pre-processing, selection, and tuning without reliance on an expert to define and configure these countless options manually. The task of traversing the near limitless combination of input features, classifier types, and associated parameters is one well-suited to automation with results that typically outperform the heuristics and insight of a seasoned expert performing this task by hand.

SensiML’s segmentation, feature pre-processing, and transform libraries includes over 80 routines built for efficient execution in the IoT sensing edge node.

Depending on selected target hardware, SensiML Analytics Studio leverages specific platform resources to improve efficiency with examples including use of Arm CMSIS DSP and Quicklogic FPGA acceleration.

ML classification spans a growing list of edge optimized algorithms including:

  • Distance based classifiers (kNN, RBF)
  • Decision trees
  • Boosted trees
  • Ensemble models
  • Neural networks

Resulting models (known as SensiML Knowledge Packs), can be assessed in bit exact device emulation of the model within Analytic Studio and delivered in binary, object, or full source code form.*

For Advanced Users:Analytics Studio Notebook

We believe teams should never outgrow the capabilities of their AutoML tools. Thus, for seasoned users we offer a more advanced version of Analytics Studio called Analytics Studio Notebook. Built on the familiar Jupyter Notebook execution environment for Python, Analytics Studio Notebook provides full control of the AutoML pipeline for users wishing to work at this level.

This gives you the tools for customizing your own functions, tuning parameters, training algorithms, and classifiers of any model. With Analytics Studio Notebook you have full model visibility and control when needed.

* Full source code output requires Standard or Enterprise level subscription.

SensiML Analytics Studio - Web Application UI

Using Analytics Studio

SensiML Analytics Studio offers a fast and convenient connected web application experience allowing multiple project team members to collaborate in labeled data analysis, AutoML model building, validation, and configuration of Knowledge Pack code for IoT endpoints.

The documentation link below provides an overview of AutoML process as implemented in SensiML Analytics Studio.

SensiML QuickStart Video Tutorial thumbnail image - Getting Started with Analytics Studio

Getting Started (AS Notebook)

Video highlights the basics of project interaction using Analytics Studio Notebook (the advanced UI for those familar with Python) and sample notebook files in the Jupyter Notebook environment. 

Segment introduces interactive Python execution in Jupyter Notebook and Pandas dataframes.

SensiML QuickStart Video Tutorial thumbnail image - Building a Model with SensiML Dashboard

Building a Model

Analogous to the Analytics Studio UI, this video shows the use of the Dashboard UI with Analytics Studio Notebook. The Dashboard UI provides a bridge between the UI-driven modeling approach and the Python pipeline within Jupyter Notebook.

The video outlines dataset query definition, data exploration, model building, knowledge pack creation, and finally deployment to the device.


Raw Signal Capture to Data Insight Labeling (Data Capture Lab Phase) to Algorithm Generation to Firmware Code Generation (Analytics Studio Phase) to Test, Validation and Support (Test App)

The SensiML Endpoint AI Workflow

Watch The Workflow Video