Google launched Visual Inspection AI, a new service to identify production defects in manufacturing units. The service uses the state-of-the-art computer vision models developed by the AI research teams at Google. Vertex AI AutoML Vision, an integral part of the managed AI platform, delivers similar capabilities. Customers can upload images and classify them based on labels before initiating a training job. AutoML Vision generates a fully-trained model hosted in the cloud or deployed at the edge for performing inference. Visual Inspection AI takes AutoML Vision to the next level through its domain knowledge of the manufacturing industry.

Building AI-powered apps can be painful. I've endured a lot of that pain because the payout of using this technology is often worth the suffering. The juice is worth the squeeze, as they say. Happily, over the past five years, developing with machine learning has gotten much easier thanks to user-friendly tooling. Nowadays I find myself spending very little time building and tuning machine learning models and much more time on traditional app development. In this post, I'll walk you through some of my favorite, painless Google Cloud AI tools and share my tips for building AI-powered apps fast.

Building AI-powered apps can be painful. I've endured a lot of that pain because the payout of using this technology is often worth the suffering. The juice is worth the squeeze, as they say. Happily, over the past five years, developing with machine learning has gotten much easier thanks to user-friendly tooling. Nowadays I find myself spending very little time building and tuning machine learning models and much more time on traditional app development. In this post, I'll walk you through some of my favorite, painless Google Cloud AI tools and share my tips for building AI-powered apps fast.

For a given audio dataset, can we do audio classification using Spectrogram? We'll be converting our audio files into their respective spectrograms and use spectrogram as images for our classification problem. A Spectrogram is a visual representation of the spectrum of frequencies of a signal as it varies with time. For this experiment, I'm going to use the following audio dataset from Kaggle For my experiment, I have rented a Linux virtual machine on Google Could Platform (GCP) and I'll be performing all the steps from there. Now that we have our audio data in place, let's create spectrograms for each audio file.

I'll show you how to use machine learning to analyze your performance in your sport of choice (mine's Tennis!). Can you ever forget the first time you grab that pass, fly down the court, and sink that puck right through the net as your fans yell adoringly from the bleachers, TOUCHDOWN! That's what you get when you spend your high school years learning calculus and icing pi on cookie cakes instead of doing sports. How many friends do you think this made me? It's time you never get back.

Ancient Egyptians used hieroglyphs over four millennia ago to engrave and record their stories. Today, only a select group of people know how to read or interpret those inscriptions. To read and decipher the ancient hieroglyphic writing, researchers and scholars have been using the Rosetta Stone, an irregularly shaped black granite stone. In 2017, game developer Ubisoft launched an initiative to use AI and machine learning to understand the written language of the Pharoahs. The initiative brought researchers from Australia's Macquarie University and Google's Art and Culture division togther.

There are hundreds of blog posts on machine learning and deep learning projects, and I've learned a lot from the ones that I've read. I wanted to add to this body of knowledge by discussing a deep learning side project that I worked on recently. I've shared the project code in a Github repo. Cloud detection in satellite images is an important classification problem. It's used heavily in the field of Remote Sensing, because clouds obscure the land underneath, and too many cloudy images in a dataset make it harder for a model to learn meaningful patterns.

Want to build an ML model but don't have enough training data? In this post I'll show you how I built an ML pipeline that gathers labeled, crowdsourced training data, uploads it to an AutoML dataset, and then trains a model. I'll be showing an image classification model using AutoML Vision in this example but the same pipeline could easily be adapted to AutoML Natural Language. Here's an overview of how it works: Want to jump to the code? The full example is available on GitHub.

At Next '18 this past July, we announced a range of updates to our AI and machine learning offerings aimed at making AI more accessible to developers. With the excitement of Next behind us, we thought we'd share a little more on these updates and how they can help you quickly and easily inject AI into your applications. Cloud AutoML is a suite of machine learning products that leverages Google's state-of-the-art transfer learning and neural architecture search (NAS) technology so you can easily train high quality custom models, even if you have limited experience with machine learning. This delivers the best of both worlds: high model quality and ease of use. This new suite of products aligns with our mission to democratize AI, and make it easy, fast and useful for all developers and enterprises.

Google is boosting its AI-as-a-service offerings this week, most notably with the alpha release of a new Contact Center AI solution. Contact Center AI is built around its Dialogflow development suite for conversational agents, which was launched last fall and already in wide use. Dialogflow Enterprise Edition now has the ability to build AI-powered virtual agents for contact centers, a Phone Gateway for taking calls without infrastructure, Knowledge Connectors for understanding unstructured data like FAQs and Sentiment Analysis. In Contact Center AI, a Virtual Agent first answers the call and handles it if possible. If not, it passes the call to a human representative, who is helped by an Agent Assist system that continues to monitor the call and provide supporting info as needed.