Machine learning models are often black boxes to end users. Without access to the underlying model architecture and parameters, they are nearly impossible to reconstruct with inputs and outputs alone.
Hosting a model in the cloud effectively prevents access to these underlying structures. Without breaching the hosting servers, an attacker has no access to the model: they can’t look at the layers, get the trained weights, or even see the framework it’s running on.
Alie Jackson has pretty much done everything. An extremely talented (and awarded) multimedia artist, she’s worked with everyone from Nike to Disney to Sony Pictures.
The Most Artistic Lens Creator of Lens Fest 2019, her work, a blend of AR and traditional media, is downright cool. Insightful, funny, bright, engaging, beautiful — I don’t have enough adjectives to describe Jackson’s style and work. You’ll just have to see for yourself.
Continue reading “Snapchat Lens Creator Spotlight: Alie Jackson”
Though it didn’t get a ton of stage time during the keynote at this year’s WWDC, there’s a lot to be excited about in the latest iteration of Apple’s machine learning framework, Core ML 3.
In this post, I’ll highlight the biggest changes to the software and discuss their implications for developers and machine learning engineers.
Companies across all industries are exploring the opportunities AI holds for their business models. While identifying AI use cases is challenging, actually implementing them adds a whole new layer of complexity.
In this process, one of the most fundamental questions you have to answer is whether to build or buy. As we’ll see in this post, the answer to this question is rarely a simple “either / or” decision.
A couple of months ago, I wrote an article about training an object detection Core ML model for iOS devices. What made this tutorial unique, though, was that I used a tool I’d built called MakeML, which allow you to start training neural networks literally in minutes. The only model type available to train in that version was a tinyYOLO based Turi Create model.
After publishing that post, many people wrote to our team letting us know that the Turi Create framework doesn’t include enough flexibility to train their models.
Warning: Before you try Janitor AI, let me warn you – it can be highly addictive.
Technically, it’s just a chatbot platform. But when you play with it, you’ll find it is highly realistic, pretty much like Character AI.
Except Janitor AI delivers NSFW content as well. Character AI is pretty “clean” that way and that’s the main selling point of Janitor AI.
Continue reading “Breaking Taboos with Janitor AI – 2024 Review”
Imagine that you have just launched a new advertising campaign, or a new product, just like Disney’s new movie “The Lion King”, and you want to have a clear view of what people think of the movie.
Natural language processing (NLP) can help with that, and specifically the task of sentiment analysis (SA).
In simple terms, this is a technique that allows you to quickly determine if people are responding positively or negatively to a given topic—in this use case movies.
Sentiment analysis would use different techniques to tokenize and analyze every word and sentence and gather as many signals to indicate whether a review is positive, negative, or neutral.
Continue reading “Using Core ML and Natural Language for Sentiment Analysis on iOS”
Imagine you have to read a document that’s very dense and has numerous words you don’t know the meanings of.
What would you do?
The answer seems obvious—get out your phone, open a search engine or online dictionary, and search for the word’s meaning.
Instead of typing, what if you could instead find out all you needed to know about a word, displayed on your smartphone, just by pointing at the word on the document?
Joseph Redmon released a series of 20 lectures on computer vision in September (2018). As he is an expert in the field, I wrote a lot of notes while going through his lectures.
4I am tidying my notes for my own future reference but will post them on Medium also in case these are useful for others.
His first lecture is an introduction in which he details the differences, methods and applications of low, mid, and high level computer vision (CV).
Continue reading “The Ancient Secrets of Computer Vision 1 by Joseph Redmon – Condensed”
As of this year, there are more than two billion active Android devices. The rapid adoption of Android phones has largely been due to the variety of smart apps, ranging from maps to photo editors. With the emergence of Deep Learning, our mobile apps are destined to become smarter.
The next generation of mobile apps powered by Deep Learning will learn and customize their functionality specifically for you.
Continue reading “Deploying PyTorch and Keras Models to Android with TensorFlow Mobile”
