#CognitiveServices – Nuevo Servicio: Anomaly Detector

Buenas!

Durante estos días, estoy totalmente centrado en un increíble evento en Avanade Canada: Canada !nnovate Event, y casi me pierdo el lanzamiento de este nuevo servicio, en la familia Cognitive Services: Anomaly Detector.

Este fin de semana tenia pensado terminar mi sesión para la próxima Global AI Night (link), sin embargo, me parece que dedicaré un poco de tiempo para poder hablar del mismo en el próximo evento.

Después de pasar hoy en día leyendo sobre el servicio, parece que funciona con series de tiempo de datos y el uso de modelos específicos, se centran en las anomalías de los datos de la serie y .. ¡Magia! Creo que la documentación oficial lo explica mejor:

The Anomaly Detector API enables you to monitor and detect abnormalities in your time series data with machine learning. The Anomaly Detector API adapts by automatically identifying and applying the best-fitting models to your data, regardless of industry, scenario, or data volume. Using your time series data, the API determines boundaries for anomaly detection, expected values, and which data points are anomalies.

Detect pattern changes in service requests

More information: https://azure.microsoft.com/en-us/services/cognitive-services/anomaly-detector/

Saludos @ Burlington

El Bruno

Advertisements

#CognitiveServices – New service: Anomaly Detector

Hi !

So, I’m fully focused on have an amazing Canadian !nnovate Event in Avanade and I almost miss this new service, in the Cognitive Services Family: Anomaly Detector.

I was planning to run my 30K Around the Bay this weekend and also finish my session for the next Global AI Night (link), however I may play around with this service and add a quick reference on the next event.

After spending sometime today reading about the service, it seems that it works with time series of data and using specific models, it focus on anomalies of data on the series and .. magic! I think the official documentation explains this better:

The Anomaly Detector API enables you to monitor and detect abnormalities in your time series data with machine learning. The Anomaly Detector API adapts by automatically identifying and applying the best-fitting models to your data, regardless of industry, scenario, or data volume. Using your time series data, the API determines boundaries for anomaly detection, expected values, and which data points are anomalies.

Detect pattern changes in service requests

More information: https://azure.microsoft.com/en-us/services/cognitive-services/anomaly-detector/

Greetings @ Toronto

El Bruno

#Azure – Single Key for all Services in #CognitiveServices, that’s cool :D

Hi !

Quick Friday post. And an amazing one, because now we have the chance to create a single Key to be use around a bunch of Cognitive Services. That’s mean we don’t need to remember and store different keys for LUIS, Face Emotion, and more. A single key will cover most of these scenarios with 3 simple steps

 

More information in What’s New? A Single Key for Cognitive Services on Channel 9 by Noelle LaCharite

Happy coding!

Greetings @ Burlington

El Bruno

#Event – I’ll be at @CodeMash on Ohio in 17 days sharing some #AI and #CustomVision experiences

codemash-logo

Hi!

I’m going to be part of one of the most amazing developer events in NA: CodeMash (http://www.codemash.org/). It will be my first time in Ohio, and also it will be an amazing opportunity to network and have some face-to-face chats with some amazing people. (Just look at the Speaker List)

I was also lucky to host a session around Artificial Intelligence with Cognitive Services at Enterprise Level. The latest announcements of containers and Cognitive Services are ready on time for this!

How a PoC at home can scale to Enterprise Level using Custom Vision APIs

It all started with a DIY project to use Computer Vision for security cameras at home. A custom Machine Learning model is the core component used to analyze pictures to detect people, animals and more in a house environment. The AI processing is performed at the edge, in dedicated hardware and the collected information is stored in the cloud.
The same idea can be applied to several CCTV scenarios, like parking lots, train stations, malls and more. However, moving this into enterprise scale brings a set of challenges, which are going to be described and explained in this session.

Session List: http://www.codemash.org/session-list/

Happy coding and see you there!

Greetings @ Toronto

El Bruno

#AI – Some news in Cognitive Services presented at #MSBuild 2018

Hi!

Again, it’s time to write about some topics what has most caught my attention in the news presented during Microsoft Build 2018. In this case I will only comment on some news related to Vision and Speech.

Vision

  • Computer Vision, now supports Object Detection. We have the ability to detect objects in an image. I have to see more in depth that we can both exploit this capacity in Custom Vision.
  • Custom Vision, new formats to export models. Until now we had the ability to export Custom Vision models to CoreML and TensorFlow.
    Now we have 2 new options that really are impressive

    • Export to ONNX. About this I wrote about it. Now we can use these models natively as part of our UWP Apps in Windows 10.
    • Export to Docker File. Especially designed for mixed scenarios with Azure Functions and Azure IOT Edge

I1

Speech

The first thing to comment is a big but very necessary change.

We now have a single service that handles: Speech to Text, Text to Speech and Speech Intent Recognition.

The 2nd point to note is that we now have the ability to Create our own Voice Models. This means that we could create Alexa or Cortana style assistants using our own voice. Ideal to give to your partner, your mother or your worst enemy.

And with this I put pause for today. Happy coding!

Greetings @ Toronto

El Bruno

 

#AI – Algunas novedades en Cognitive Services presentadas en #MSBuild 2018

Buenas!

Otra vez apunto el post a lo que mas me ha llamado la atención en las novedades presentadas en Microsoft Build 2018. En este caso solo comentare algunas novedades relacionadas a Vision y Speech.

Vision

  • Computer Vision, ahora soporta Object Detection. Tenemos la capacidad de detectar objetos en una imagen. Tengo que ver mas a fondo que tanto podemos explotar esta capacidad en Custom Vision.
  • Custom Vision, nuevos formatos para exportar modelos. Hasta ahora teníamos la capacidad de exportar modelos de Custom Vision a CoreML y a TensorFlow. Ahora tenemos 2 nuevas opciones que realmente son impresionantes
    • Exportar a ONNX. Sobre esto ya escribí al respecto. Ahora podremos utilizar estos modelos de forma nativa como parte de nuestras UWP Apps en Windows 10.
    • Exportar a Docker File. Especialmente pensado para escenarios mixtos con Azure Functions y Azure IOT Edge

I1

Speech

Lo primero a comentar es un cambio grande pero muy necesario.

Ahora tenemos un único servicio que se encarga de: Speech to Text, Text to Speech y Speech Intent Recognition.

El 2do punto a destacar es que ahora tenemos la capacidad de crear nuestros propios Voice Models. Esto significa que podríamos crear asistentes del estilo Alexa o Cortana utilizando nuestra propia voz. Ideal para regalar a tu pareja, tu madre o a tu peor enemigo.

Y con esto pongo pausa por today. Happy coding!

Saludos @ Toronto

El Bruno

 

#AI – Real-time audio translation using #CognitiveServices

Hi!

I still have some work to do after the Azure Global Bootcamp. After showing the Audio Bot in live mode, one of the classic questions in Canada, is that what happens with French?, is this supported?

Well, Cognitive Services offers us several services that can be useful to create multi cultural apps, mostly if we are working with text or audio. Regardless of the Cognitive Service operation that we use, the process to perform an audio translation is usually always the following

  • Convert audio into text
  • Convert the text from a language A to a language B

In the first step, it is possible to use local services of the device to convert the audio into text, or if you work with a specific business domain, Custom Speech Service is the service to use.

Another option, which is also interesting is to use Translator Speech API. This service uses an audio stream as input and with a single call to an Http Endpoint. It is worth seeing the implementation of the service, since it works with WebSockets sending chunks of data from an audio file.

The best thing as always is to go to the code examples of the Microsoft Translator repository and see how they have been implemented. In the example for WPF we can see that we define options like source and destination language, text in subtitles and more.

capture_001_30042018_190722

At the moment of initial service, the code connects to the EndPoint and starts sending the audio that is recorded from the Input Device

capture_002_30042018_190726

Almost in real time, we can see how the application translates between 2 languages

capture_003_30042018_190735

In addition to the WPF example, in repos we can see examples for iOS, Android, UWP and more.

Happy Coding!

Greetings @ Toronto

El Bruno

References

#AI – Traducción en tiempo real de audio utilizando #CognitiveServices

Buenas!

Sigo con los pendientes después del Azure Global Bootcamp. Después de mostrar el Audio Bot, una de las preguntas clásicas en Canada, ¿es que pasa con el Frances?

Pues bien, Cognitive Services nos ofrece varios servicios que pueden sernos de utilidad. Independientemente de los servicios de CS que utilicemos, el proceso suele ser siempre el siguiente

  • Convertir el audio en texto
  • Convertir el texto de un idioma A a un idioma B.

En el primer paso es posible utilizar servicios locales del dispositivo para convertir el audio en texto, o si trabajas con un dominio de negocios especifico, Custom Speech Service es el servicio a utilizar.

Otra opción, que también es interesante es utilizar Translator Speech API. Este servicio utiliza un stream de audio como input y con una única llamada a un Http Endpoint. Vale la pena ver la implementación del servicio, ya que funciona con WebSockets enviando chunks de datos de un archivo de audio.

Lo mejor como siempre es ir a los ejemplos de código del repositorio de Microsoft Translator y ver como se han implementado los mismos. En el ejemplo para WPF podemos ver que definimos opciones como idioma de origen y destino, texto en subtítulos y más.

capture_001_30042018_190722

Al momento de inicial el servicio, el código se conecta al EndPoint y comienza a enviar el audio que se graba desde el Input Device

capture_002_30042018_190726

Casi en tiempo real, podemos ver como la aplicación traduce entre 2 idiomas

capture_003_30042018_190735

Además del ejemplo WPF, en los repos podemos ver ejemplos para iOS, Android, UWP y mas.

Happy Coding!

Greetings @ Toronto

El Bruno

References

#Flow –Analyzing images in #Sharepoint Lists using #CognitiveServices

Hi!

One of the examples of using Cognitive Services that I commented during the Global Azure Bootcamp was the automatic analysis of information on items in SharePoint lists. To achieve this we can create a Flow with the following steps

  • Trigger, Flow is triggered when a new Item is added to the SharePoint list
  • Get the contents of the file associated with the Item in the SharePoint list
  • Use Cognitive Services to obtain the tags and the description of the image
  • Update the Item Description with the information returned by CS

I1

After uploading a couple of images to the Sharepoint list we can see that the process works correctly

I11

If we see the description of each of the items we can see that the items have been updated correctly

 

The historical also shows us the correct step by step.

I2

However, in the history of 5 images, there are 2 that have failed. One of the advantages of working with Flow, is that, in the history of executions, it is easy to verify what step has failed. In this case, the last 2 images do not have the correct format to be analyzed with Cognitive Services

I3

Happy Coding!

Greetings @ Toronto

El Bruno

References

My posts on Flow

#Flow – Analizando imágenes en Listas de #Sharepoint utilizando #CognitiveServices

Buenas!

Uno de los ejemplos de utilización de Cognitive Services que comente durante el Global Azure Bootcamp consistía en el análisis automático de información en ítems de listas de SharePoint. Para lograr esto podemos crear un Flow con los siguientes pasos

  • Trigger, el Flow se dispara cuando se agrega un nuevo Item en la lista de SharePoint
  • Obtener el contenido del archivo asociado al Item de la lista de SharePoint
  • Utilizar Cognitive Services para obtener los tags y la descripción de la imagen
  • Actualizar la Descripción del Item con la información retornada por CS

I1

Luego de subir un par de imágenes a la lista de Sharepoint podremos ver que el proceso funciona correctamente

I11

Si vemos la descripción de cada uno de los ítems podremos ver que los ítems se han actualizado correctamente

 

El histórico también nos muestra el paso a paso correcto.

I2

Sin embargo, en el histórico de 5 imágenes, hay 2 que han fallado. Una de las ventajas de trabajar con Flow, es que, en el histórico de ejecuciones, es fácil comprobar que paso ha fallado. En este caso, las ultimas 2 imágenes no tienen el formato correcto para ser analizadas con Cognitive Services

I3

En próximos posts, otros escenarios donde utilizar CS puede ayudarnos con tareas del día a día.

Happy Coding!

Greetings @ Toronto

El Bruno

References

My posts on Flow