Recent advances in semi-supervised learning with deep generative models have shown promise in generalizing from small labeled datasets ($\mathbf{x},\mathbf{y}$) to large unlabeled ones ($\mathbf{x}$). In the case where the codomain has known structure, a large unfeatured dataset ($\mathbf{y}$) is potentially available. We develop a parameter-efficient, deep semi-supervised generative model for the purpose of exploiting this untapped data source. Empirical results show improved performance in disentangling latent variable semantics as well as improved discriminative prediction on Martian spectroscopic and handwritten digit domains.

Anima Anandkumar pioneered the research of finding global optimal in non-convex problems, a big pain point in machine learning. Our protagonist for this week's Techie Tuesdays, Anima is an academician who represents the best of both worlds--industry and academia. She has contributed significantly to major AI and ML projects at Amazon. This is a treat for all machine learning enthusiasts. In my two hours of conversation with Anima Anandkumar, Principal Scientist at Amazon Web Services, I was injected with the most potent dose of technical knowledge. Not that I didn't expect it while talking to an ex-faculty of UC Irvine (soon to be an endowed professor at Caltech), known for her research on non-convex problems (in deep learning). Our Techie Tuesdays protagonist of the week, Anima has worked towards establishing a strong collaboration between academia and industry. She follows an unconventional style of teaching, the one she would have loved as a student.

Amazon Rekognition is a service that makes it easy to add image analysis to your applications. It's based on the same proven, highly scalable, deep learning technology developed by Amazon's computer vision scientists to analyze billions of images daily for Amazon Prime Photos. Facial recognition enables you to find similar faces in a large collection of images. In this post, I'll show you how to build your own face recognition service by combining the capabilities of Amazon Rekognition and other AWS services, like Amazon DynamoDB and AWS Lambda. This enables you to build a solution to create, maintain, and query your own collections of faces, be it for the automated detection of people within an image library, building access control, or any other use case you can think of.

Today, many companies use big data to make super relevant recommendations and growth revenue. Among a variety of recommendation algorithms, data scientists need to choose the best one according a business's limitations and requirements. To simplify this task, the Statsbot team has prepared an overview of the main existing recommendation system algorithms. Collaborative filtering (CF) and its modifications is one of the most commonly used recommendation algorithms. Even data scientist beginners can use it to build their personal movie recommender system, for example, for a resume project.

Demis Hassabis, founder of DeepMind, recently spoke out about his vision on how to reach the "next level," of artificial intelligence. His strategy is, predictably, to reconnect with the field of neuroscience, to study natural intelligence, in the hope of mimicking these processes inside the machine. While I have shortly cover my opinion on this before, I want to take another pass over this topic to see if the opinions of multiple high ranking experts are able to make me change my mind about human like artificial intelligence.

The last months, I have worked on brand logo detection in R with Keras. The goal is to build a (deep) neural net that is able to identify brand logos in images. Just to recall, the dataset is a combination of the Flickr27-dataset, with 270 images of 27 classes and self-scraped images from google image search. In case you want to reproduce the analysis, you can download the set here. In the last post, I used the VGG-16 pretrained model and showed that it can be trained to achieve an accuracy of 55% on the training 35% on the validation set.

Software giant Microsoft has announced its Project Brainwave deep learning acceleration platform for real-time artificial intelligence (AI). With the help of ultra-low latency, the system processes requests as fast as it receives them. "Real-time AI is becoming increasingly important as cloud infrastructures process live data streams, whether they be search queries, videos, sensor streams, or interactions with users," said Doug Burger, an engineer at Microsoft, in a blog post late on Tuesday. The'Project Brainwave' uses the massive field-programmable gate array (FPGA) infrastructure that Microsoft has been deploying over the past few years. "By attaching high-performance FPGAs directly to our datacentre network, we can serve DNNs as hardware microservices, where a DNN can be mapped to a pool of remote FPGAs and called by a server with no software in the loop," Burger said.

Data driven algorithms like neural networks have taken the world by storm. They recent surge is due to several factors, including cheap and powerful hardware, and vast amounts of data. Neural Networks are currently the state of the art when it comes to'cognitive' tasks like image recognition, natural language understanding, etc.,but they don't have to be limited to such tasks. In this post I will discuss a way to compress images using Neural Networks to achieve state of the art performance in image compression, at a considerably faster speed. This article assumes some familiarity with neural networks, including convolutions and loss functions.

Last week was the high point of the Dota 2 competitive year: it was the week of The International, Valve's biggest tournament. On Saturday, Team Liquid walked away with more than $10 million after defeating Newbee 3-0 in the grand final. Right now, one of the requirements to be a good Dota 2 player is that you've got to be a living, breathing human. The game does include some basic computer-controlled bots to practice against, but any seasoned player of the game should have no trouble prevailing over these bots, even on their hardest "Unfair" difficulty (though the Unfair Viper bot is a legendary jerk that's utterly miserable to play against). Last Friday, however, we got a hint of a new, altogether more threatening kind of computer-controlled player: an AI-controlled bot built by Elon Musk's OpenAI.

In part one of this series we covered some of the history and theoretical basics of Artificial Neural Networks (ANNs). Now it's time to look at what changed to lead us to where we are today. In the pre-cloud era, time, cost and computational constraints meant that large scale research was prohibitively difficult. It was also unclear exactly how to scale ANNs out to hundreds of layers and thousands of neurons. And even if it was possible, could you get any results worth using? So given how difficult it was, it's worth asking what the motivation was in the first place.