Archive of posts with tag 'machine-learning'

From multilingual speech to subtitles

From multilingual speech to subtitles How to build a multilingual video automatic subtitles system Recently we have participated in a public tender related to the need of an innovative automatic...

How to Build a Generative AI Chatbot with RAG Source on AWS

Overview Retrieval Augmented Generation (RAG) is a technique that combines the strengths of traditional retrieval-based and generative AI-based approaches to question-answering (QA) systems. In a RAG chatbot, the user’s query...

Generative AI based medical assistant on AWS

Yet another LLM-based chatbot Generative AI and large language models (LLMs) are becoming increasingly popular, and small and big tech companies are releasing new solutions like ChatGPT, Bard, and Llama...

Discover the potential of Search Commerce with GPT: Our feedback

In the world of online commerce, search is a key element in attracting and converting potential customers. Today, we’re going to tell you about a technology that is revolutionizing the...

Your private GPT to chat with your documents

A step-by-step guide to build a chatbot that can answer any questions about what’s in your documents What if we build another chatbot? People accustomed to the chatbot concept, and...

Starting from scratch, how to embed computer vision techniques into your project #4

Part 4— Integration How to integrate it? The SageMaker work is done. We have a data set with labels, a trained model, and an endpoint to request objects detection. But...

Starting from scratch, how to embed computer vision techniques into your project #3

Part 3 — Model training Open your book at chapter 1: what is a screwdriver? We have now nearly reached the training phase. To start this phase, the only missing...

Starting from scratch, how to embed computer vision techniques into your project #2

Part 2 — Training data set Ok, let’s do it A lot of Screwdrivers First, we need a significant amount of screwdrivers (and hammer, paintbrush, etc.) images. And to teach...

Starting from scratch, how to embed computer vision techniques into your project

A practical guide to answering this question: is this a screwdriver or a hammer? Smile is the proud editor of ElasticSuite, a great Magento open-source extension, with more than a...

Smile Innovation’s watch #22

Wow! What a 🏃‍♂️final sprint until the finish line of the year for us! It’s a long time without a Techwatch. Enough to made us lost count of exciting news,...

Innovation Watch #16

This content was sent on july, 10th via our Tech Watch Newsletter We’re still in the early days of July and it feels more comfortable, the air is breathable again....

Smile Innovation Watch #14

*This content was sent on june, 7th via our Tech Watch Newsletter* Is it already June? Damn how times fly 😅 It starts to be warm enough to enjoy a...

Training neural network with image sequence, an example with video as input

How can we classify actions that happen on video? How to use Time Distributed layers with image sequence? How to manage the input shapes? Last time, we explain how works...

How to work with Time Distributed data in a neural network

And how to use it for videos input, movements detection, gestures recognition… ⚠ Important note: There is an error in explanation I give in the article. I often say that...

AWS Greengrass the forefront of edge computing

This articles main goal is to resume briefly what AWS Greengrass is. If you want a more thorough presentation you can find it on the AWS Greengrass documentation page IoT...

LSTM, Intelligence artificielle sur des données chronologiques

Ou comment un réseau de neurones peut interpréter une série de données dite “temporelle” Si vous avez un tant soit peu travaillé avec des réseaux de neurones, vous avez certainement...

Imannotate, opensource collaborative image annotation for machine learning

We made a tool to annotate images with teammates, easy to install and extensible. And obviously, it’s open source! In the machine learning and deep learning world, one of the...

How to make profits in cryptocurrency trading with machine learning

The interest around cryptocurrency technology grows day after day, and the research about Machine learning has never been so fast. Could a machine trained to trade cryptocurrency make profits ?...

Hey Snips!

Or how I made my child study multiplications tables thanks to Snips OK, I will assume that you have already heard about voice assistants considering the buzz around them. Yes...

SageMaker : Bring your own Algorithms

With the help of Docker, you will be able to customize training and infering models using other frameworks that those provided by SageMaker You may already know what Amazon SageMaker...

Smile Innovation's watch - #2

For this second edition of our watch, we wanted to show you an amazing picture first. The latest TIME’s cover, made by 958 drones working altogether. Then we’ll talk Machine...

Smile Innovation's watch - #1

Hello world 🌎! As you might (or might not) know Smile Innovation is in charge of watching, ideating, prototyping, evangelizing for both people within the group and Smile’s fellow customers....

Capturing your dinner, a deep learning story

A naive approach to features extraction and R-CNN Working for Smile innovation can lead to funny pre-sales research. Few weeks ago I was involved in a discussion to find out...