My recommendation is to get video examples from throughout the week, with different lighting, different'scenarios' on the street such as cars, bins, animals, ghosts, whatever else is common. In my case, I need video with and without those bins. Now comes the fun part. Go ahead and download this nifty tool from Machine Box called Objectbox. Follow the instructions to get yourself setup with the annotation tool in Objectbox, and place your videos into the boxdata/files directory.

This story is a step-by-step guide to how I built a language detection model using machine learning (that ended up being 97% accurate) in under 20 minutes. Language detection is a great use case for machine learning, more specifically, for text classification. Given some text from an e-mail, news article, output of speech-to-text capabilities, or anywhere else, a language detection model will tell you what language it is in. This is a great way to quickly categorize and sort information, and apply additional layers of workflows that are language specific. For example, if you want to apply spell checking to a Word document, you first have to pick the correct language for the dictionary being used.

As someone who needs to run a business, big or small, you are inundated with articles and talks at conferences about how great AI is. You hear a lot about what it can do, about the outcomes of some sexy new research, and about vague assertions of how it will transform your business. In truth, it can and will transform your business, but only if you can overcome the barriers to entry. There is a lot of focus on the artificial intelligence itself; the machine learning model and its algorithms, its accuracy, and all the amazing new breakthroughs. This is all well and good, and definitely worth paying attention to.

When a machine learning model misses something, its really easy to just think its a bug, or perhaps a defect in the model. It is vitally important you understand that that is not the case. False positives and false negatives are part and parcel of what machine learning is. It makes mistakes sometimes, just like we do. Every business has to be prepared for occasional false positives and negatives in machine learning.

With Facebox, using a simple http API, you can do face detection and recognition in your own data. Facebox can also be taught to recognise any number of people. To recognise people you have to invoke /facebox/teach with a name,id and an image with a single face on it. You only need one photo per person. After you've taught Facebox with the people you want it to recognize, you can start recognising faces by invoking the /facebox/check endpoint.

Textbox is the latest box from Machine Box, and has just been released as a BETA preview. It offers Natural language processing, keyword extraction and sentiment analysis of unstructured text. Here's a video of the Text analyzer demo we built to show off the capabilities (you can play with this for yourself, by running Textbox on your laptop; scroll down to learn more). Being able to have machines understand unstructured textual content (like tweets, reviews, comments, questions, emails, etc.) already plays a big part in our life. Apple's Siri, Amazon's Echo, Google Home, and any device that you can speak to uses some form of natural language processing in order to understand what you're saying to it.