Blog

Low Rank Approximation Implementation 1/4

Tech

Singular Value Decomposition (SVD) - Model Compression : Resnet18

Leila Mozaffari

Low Rank Approximation Implementation 2/4

Tech

Singular Value Decomposition (SVD) - Model Compression : Resnet50

Leila Mozaffari

Low Rank Approximation Implementation 4/4

Tech

Singular Value Decomposition (SVD) - Dimensionality Reduction

Leila Mozaffari

Low Rank Approximation Implementation 3/4

Tech

Singular Value Decomposition (SVD) - Dimensionality Reduction

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…

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…

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…

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…

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…

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

Enabling citizens and businesses to create smart city solutions effortlessly

UseCase

Knowledge Distillation Implementation 2/3

Tech

2. Hint-Based Distillation

Leila Mozaffari

Knowledge Distillation Implementation 3/3

Tech

3. Self-Distillation

Leila Mozaffari

Knowledge Distillation Implementation 1/3

Tech

1. Soft Label Distillation

Leila Mozaffari

Low-rank approximation 1/4

Tech

Overview of Low-rank approximation - Part1

Leila Mozaffari

Low-rank approximation 2/4

Tech

Overview of Low-rank approximation – Part2

Leila Mozaffari

Low-rank approximation 3/4

Tech

Overview of Low-rank approximation – Part3

Leila Mozaffari

Low-rank approximation 4/4

Tech

Overview of Low-rank approximation – Part4

Leila Mozaffari

Knowledge Distillation

Tech

Overview of Knowledge Distillation: Simplifying Deep Learning Models

Leila Mozaffari

Demistifying TinyMLaaS

Tech

TinyMLaaS

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

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 …

tinyRuntime review

Tech

Reviewing the current status of our lightweight runtime

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…

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…

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…

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…

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…

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.

Demystifying PyTorch Static Quantization

Tech

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

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.

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.

AI Compression as-a-Service MVP6 review

News

MVP

Our internal review of MVP6 usage

Edge Impulse Review

Tech

SaaS

Competitor

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

TinyML as-a-Service Overview

Tech

SaaS

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

IREE review

Tech

Compiler

Brief overview of IREE

Imagimob Studio Review

Tech

SaaS

Competitor

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

AI compression SaaS

Tech

SaaS

Brief overview of AI Compression

TinyML Use Cases

Tech

SaaS

UseCase

Use cases for TinyML offered by NinjaLABO

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.

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.