Ask Sendai

Classical machine learning and deep learning algorithms can only propose the most probable solutions and are not able to adequately model uncertainty. The success of deep neural networks in diverse areas as image recognition and natural language processing has been outstanding in recent years. However, classical machine learning and deep learning algorithms can only propose the most probable solutions and are not able to adequately model uncertainty. In this talk, Chi Nhan Nguyen demonstrates how appropriate modelling of uncertain knowledge and reasoning leads to more informative results that can be used for better decision making.

We’ve seen profound advances in technology, especially with the development of artificial intelligence and deep learning which are increasingly for voice assistants. This, in turn, promises to bring about huge changes in consumer behavior — what’s being called “voice commerce”. This is a new channel, governed by a new set of rules. Here, communication is key. These shopping assistants use AI and are changing the rules of the game when it comes to customers’ purchasing behavior; they can even make purchasing decisions for the customer if desired.

Natural language understanding (NLU) and language translation are key to a range of important applications, including identifying and removing harmful content at scale and connecting people across different languages worldwide. Although deep learning–based methods have accelerated progress in language processing in recent years, current systems are still limited when it comes to tasks for which large volumes of labeled training data are not readily available. Recently, Facebook AI has achieved impressive breakthroughs in NLP using semi-supervised and self-supervised learning techniques, which leverage unlabeled data to improve performance beyond purely supervised systems.

Computerized question-answering systems usually take one of two approaches. Either they do a text search and try to infer the semantic relationships between entities named in the text, or they explore a hand-curated knowledge graph, a data structure that directly encodes relationships among entities. With complex questions, however — such as “Which Nolan films won an Oscar but missed a Golden Globe?” — both of these approaches run into difficulties.

Michigan team builds memristors atop standard CMOS logic to demo a system that can do a variety of edge computing AI tasks Hoping to speed AI and neuromorphic computing and cut down on power consumption, startups, scientists, and established chip companies have all been looking to do more computing in memory rather than in a processor’s computing core. Memristors and other nonvolatile memory seem to lend themselves to the task particularly well.

EGG is a new toolkit that allows researchers and developers to quickly create game simulations in which two neural network agents devise their own discrete communication system in order to solve a task together. For example, in one of the implemented games, one agent sees a handwritten digit and has to invent a communication code to tell the other agent which number it represents. A lively area of machine learning (ML) research, language emergence would benefit from a more interdisciplinary approach.

Creating accurate maps today is a painstaking, time-consuming manual process, even with access to satellite imagery and mapping software. Many regions — particularly in the developing world — remain largely unmapped. To help close this gap, Facebook AI researchers and engineers have developed a new method that uses deep learning and weakly supervised training to predict road networks from commercially available high-resolution satellite imagery. The resulting model sets a new bar for the state of the art for accuracy, and because it is able to accommodate regional differences in road networks, it can effectively predict roads around the globe.

Tools that enable fast and flexible experimentation democratize and accelerate machine learning research. Take for example the development of libraries for automatic differentiation, such as Theano, Caffe, TensorFlow, and PyTorch: these libraries have been instrumental in catalyzing machine learning research, enabling gradient descent training without the tedious work of hand-computing derivatives. In these frameworks, it’s simple to experiment by adjusting the size and depth of a neural network, by changing the error function that is to be optimized, and even by inventing new architectural elements, like layers and activation functions–all without having to worry about how to derive the resulting gradient of improvement.

This panel is a very diverse group, and I’m actually going to let them introduce themselves rather than me trying to butcher any names. This is all about answering my need, literally, my first steps. What should I be focused on as a software engineer wanting to get into ML and start using ML more convinced leadership on things that I want to do? For example, I work for an edge company deploying use cases at edge, so I want to be able to use machine learning to be able to anomaly-detect things at the edge.

In 2018, we published a blog post titled Categorizing Listing Photos at Airbnb. In that post, we introduced an image classification model which categorized listing photos into different room types and helped organize hundreds of millions of listing photos on the Airbnb platform. Since then, the technology has been powering a wide range of internal content moderation tools, as well as some consumer-facing features on the Airbnb website. We hope such an image classification technology makes our business more efficient, and our products more pleasant to use.