Blog

TalkingTeddy: The Future of Pediatric Patient Care

Real-time Interactive Projection for Children
LLM
Helsinki
Jetson
NinjaLABO is pushing the boundaries of edge AI with its latest creation: an AI-powered teddy bear that can talk, feel, and respond to human interaction—all running entirely…
Apr 25, 2025
Hiroshi Doyu

KauKo:ClickBounce

AI gamification of Youth Exercise Activation
LLM
Helsinki
Jetson
NinjaLABO’s latest project, KauKo:ClickBounce, transforms any indoor wall into an interactive gaming surface using just a projector, camera, and AI-powered mini-computer.…
Apr 24, 2025
Hiroshi Doyu

Fine-tuning ResNet18 with Imagenette on Jetson Orin Nano

Tech
Jetson

Learn how to fine-tune ResNet18 on the Jetson Orin Nano using the Imagenette dataset for efficient image classification.

Feb 28, 2025
Nghi Vo Dong

How to Easily Install PyTorch on Jetson Orin Nano running JetPack 6.2

Tech
Jetson

Follow this step-by-step guide to install PyTorch on the Jetson Orin Nano running JetPack 6.2.

Feb 27, 2025
Nghi Vo Dong

Real-World Solutions with LLMCAM and GPT Function Calling [4/4]

Tech
LLM

Tutorial for building a notification service with GPT Function calling

Feb 12, 2025
Nghi Vo Dong

Real-World Solutions with LLMCAM and GPT Function Calling [3/4]

Tech
LLM

Tutorial for integrating our image processing pipeline into GPT Function calling

Feb 12, 2025
Nghi Vo Dong

Real-World Solutions with LLMCAM and GPT Function Calling [2/4]

Tech
LLM

Tutorial for integrating various services into your GPT Function calling ecosystem

Feb 12, 2025
Nghi Vo Dong

Real-World Solutions with LLMCAM and GPT Function Calling [1/4]

Tech
LLM

Tutorial for constructing your own GPT Function calling ecosystem using our LLMCAM application

Feb 12, 2025
Nghi Vo Dong

KauKo:ClickBounce

AI gamification of Youth Exercise Activation
LLM
Helsinki
Jetson
NinjaLABO is revolutionizing outdoor play with KauKo:ClickBounce, transforming playgrounds into immersive gaming arenas using AI. By projecting games onto walls or surfaces…
Jan 13, 2025
Hiroshi Doyu

Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction (CVPRW 2022)

Tech

HSI

Dec 12, 2024
Leila Mozaffari

Low Rank Approximation Implementation 4/4

Tech

Singular Value Decomposition (SVD) - Dimensionality Reduction

Oct 24, 2024
Leila Mozaffari
 

Low Rank Approximation Implementation 3/4

Tech

Singular Value Decomposition (SVD) - Dimensionality Reduction

Oct 24, 2024
Leila Mozaffari
 

Low Rank Approximation Implementation 2/4

Tech

Singular Value Decomposition (SVD) - Model Compression : Resnet50

Oct 24, 2024
Leila Mozaffari

Low Rank Approximation Implementation 1/4

Tech

Singular Value Decomposition (SVD) - Model Compression : Resnet18

Oct 24, 2024
Leila Mozaffari

Programmable Platform with ChatGPT API

Tech
Web
LLM
The goal is to develop a platform that enables users to dynamically create and manage services through natural language commands. This platform will leverage ChatGPT alongsid…
Oct 22, 2024
Hiroshi Doyu

The Impact of GPTs + Function-Calling on Web Development

Tech
Web
It’s the weekend, and I spent some time researching how to develop our LLM-based services. What I discovered is how GPTs + function calling are transforming traditional web…
Oct 20, 2024
Hiroshi Doyu

LangChain + LangGraph vs. OpenAI Swarm + GPTs + Function Calling: A Comparison for Web Service Development

Tech
Web
LLM
At NinjaLABO, we’re always on the lookout for the most effective tools and platforms for AI-powered web service development. As we explore different architectures for…
Oct 20, 2024
Hiroshi Doyu

How to Build an LLM Web Service Effortlessly with OpenAI Swarm, GPTs, Function Calling, and Anthropic Artifacts

Tech
Web
LLM
Building an LLM-based web service can be a complex process, requiring you to balance scalability, flexibility, real-time data handling, and user interaction. But by using…
Oct 20, 2024
Hiroshi Doyu

Anthropic Projects vs. OpenAI GPTs: A Comparison for LLM-Based Web Service Development

Tech
Web
LLM
As AI continues to evolve, organizations are seeking the best platforms to build scalable, efficient, and secure web services using large language models (LLMs). Two key…
Oct 20, 2024
Hiroshi Doyu

Hack Your City: Empowering Smart Solutions with No Code Vision LLM

Enabling citizens and businesses to create smart city solutions effortlessly
UseCase

Oct 11, 2024
Hiroshi Doyu

Knowledge Distillation Implementation 3/3

Tech
  1. Self-Distillation
Oct 10, 2024
Leila Mozaffari

Knowledge Distillation Implementation 2/3

Tech
  1. Hint-Based Distillation
Oct 10, 2024
Leila Mozaffari

Knowledge Distillation Implementation 1/3

Tech
  1. Soft Label Distillation
Oct 10, 2024
Leila Mozaffari
 

Low-rank approximation 4/4

Tech

Overview of Low-rank approximation – Part4

Oct 7, 2024
Leila Mozaffari
 

Low-rank approximation 3/4

Tech

Overview of Low-rank approximation – Part3

Oct 7, 2024
Leila Mozaffari

Low-rank approximation 2/4

Tech

Overview of Low-rank approximation – Part2

Oct 7, 2024
Leila Mozaffari

Low-rank approximation 1/4

Tech

Overview of Low-rank approximation - Part1

Oct 7, 2024
Leila Mozaffari

Knowledge Distillation

Tech

Overview of Knowledge Distillation: Simplifying Deep Learning Models

Oct 1, 2024
Leila Mozaffari

Demistifying TinyMLaaS

Tech
TinyMLaaS

Brief overview of the technology behind NinjaLABO’s TinyML as-a-Service

Sep 27, 2024
Nghi Vo

tinyRuntime review

Tech

Reviewing the current status of our lightweight runtime

Sep 26, 2024
Haruka Doyu

LLM on Camera as an Universal Sensor for Smart Mobility - Privacy-Preserving Edge AI PoC

Beyond 1984: Smart Cities Powered by Ethical AI and Citizen Empowerment
UseCase
NinjaLABO proposes a 1.5-month Proof of Concept (PoC) to demonstrate the transformative potential of Local Large Language Models (LLMs) on edge cameras as a Universal Sensor …
Sep 26, 2024
Hiroshi Doyu

ToDo list in Autumn 2024

WoW
This document provides an overview of NinjaLABO’s tasks and objectives for the autumn of 2024. The following sections outline key areas of focus, ranging from way of working…
Sep 11, 2024
Hiroshi Doyu

Summer Insights: Evolving tinyMLaaS with Flexible Pipelines and Distributed Execution

Tech
DNN
This summer, our team embarked on an ambitious journey, iterating through eight MVP releases of our tinyMLaaS platform, which focuses on deep neural network (DNN) model…
Sep 4, 2024
Hiroshi Doyu

Looking for Software Engineer - AI Model Compression & DNN Runtime

Hiring
NinjaLABO is a fresh, finnish startup at the forefront of AI innovation, focusing on AI model compression and deep neural network (DNN) runtime optimization for IoT…
Aug 29, 2024
Hiroshi Doyu

Optimizing a DNN Model for Processing Hyperspectral Imaging (HSI) Data

Tech
DNN
Hyperspectral Imaging (HSI) is a powerful technique that captures a wide spectrum of light across dozens to hundreds of narrow wavelength bands. Unlike traditional RGB…
Aug 20, 2024
Hiroshi Doyu

Comprehensive Overview of DNN Model Compression Techniques

Tech
DNN
Deep Neural Networks (DNNs) have achieved remarkable success across various domains, from image recognition to natural language processing. However, their deployment…
Aug 18, 2024
Hiroshi Doyu

Building a Real-Time Face Identification System: A Comprehensive Guide

Tech
UseCase

Explore how to build a real-time face identification system using Ultralytics YOLOv8, a state-of-the-art object detection model known for its speed and accuracy. We’ll compare various tools, including managed services like AWS Rekognition and Azure Face API, to help you choose the best solution for your needs. Whether you’re a developer seeking full control over your models or looking for an easy-to-integrate, scalable solution, this guide will provide you with the knowledge and tools to create a powerful face identification system.

Aug 18, 2024
Hiroshi Doyu
 

Demystifying PyTorch Static Quantization

Tech

A deep dive into how PyTorch performs inference with quantized models.

Aug 12, 2024
Haruka Doyu

TinyML as-a-Service with Helsinki University summer course 2023

HU
TinyMLaaS

This is the main repository of Tiny Machine Learning as a Service project for Software Engineering Project course at University of Helsinki, summer 2023.

Aug 6, 2024
Hiroshi Doyu

About

About
Team

The team of experts in software development, research, and design is working to enable businesses to integrate AI & Machine Learning applications on a wide range of devices without relying on expensive networking & cloud computing services thanks to their solution, TinyML as a Service.

Aug 6, 2024
Hiroshi Doyu

AI Compression as-a-Service MVP6 review

News
MVP

Our internal review of MVP6 usage

Aug 6, 2024
Nghi Vo

Edge Impulse Review

Tech
SaaS
Competitor

Edge Impulse - A Comprehensive Review of the Leading Edge AI Platform

Aug 5, 2024
Nghi Vo

TinyML as-a-Service Overview

Tech
SaaS

Brief overview of NinjaLABO’s TinyML as-a-Service / AI compression as-a-Service

Jul 17, 2024
Hiroshi Doyu

IREE review

Tech
Compiler

Brief overview of IREE

Jul 12, 2024
Haruka Doyu

Imagimob Studio Review

Tech
SaaS
Competitor

Brief overview of Imagimob Studio - A solution for Edge AI applications

Jul 8, 2024
Nghi Vo

TinyML Use Cases

Tech
SaaS
UseCase

Use cases for TinyML offered by NinjaLABO

Jul 2, 2024
Hiroshi Doyu

AI compression SaaS

Tech
SaaS

Brief overview of AI Compression

Jul 2, 2024
Hiroshi Doyu

How can we democratize machine learning on IoT devices?

Ericsson

Making tiny machine learning widely available on edge IoT devices could prove to be a major leap in smart sensing across industries. Below, we plot the technical milestones to making that happen as part of our ongoing research into TinyML as-a-service.

Aug 6, 2020
Hiroshi Doyu

TinyML as-a-Service and the challenges of machine learning at the edge

Ericsson

The TinyML as-a-Service project at Ericsson Research sets out to address the challenges that today limit the potential of machine learning (ML) paradigms at the edge of the embedded IoT world. In this post, the second post in our TinyML series, we take a closer look at the technical and non-technical challenges on our journey to making that happen. Learn more below.

Aug 6, 2019
Hiroshi Doyu
No matching items