Where on Earth is AI Headed?
Ten years ago, computers could not understand spoken words well, but today we routinely speak to our mobile phones, and computer vision algorithms have now reached human or super-human level performance for many types of images. Self-driving cars are already appearing on our streets, and a deep network called GPT-3 writes surprisingly human-like paragraphs of […]
Read More
Fuzzing to improve the security and reliability of cloud services with RESTler
In the past few years, cloud services have experienced tremendous growth. Most of these services are programmatically accessed through REST APIs. As the pace of development increases, both the APIs and service implementations are evolving rapidly. There is an urgent need for automated tools to test the reliability and security of cloud services that can […]
Read More
The Theoretical Aspects of Gradient Methods in Deep Learning
In this talk from Microsoft Research Asia, Jian Li of Tsinghua University explains Theoretical Aspects of Gradient Methods in Deep Learning by
Read More
Fourier Feature Networks and Neural Volume Rendering
Fourier Feature Networks are an exciting new development in Computer Vision, and their use for modeling radiance fields has produced a range of impressive results at the meeting point of Computer Vision and Computer Graphics. In this lecture, Matthew covers the motivation behind using Fourier features in neural network training, introduces the fundamentals of volumetric […]
Read More
DIABLo: a Deep Individual
Here’s an interesting video from Microsoft Research In this project, we have developed and studied a deep neural network-based individual-agnostic general-purpose binaural localizer (BL) for sound sources located at arbitrary directions on the $4\pi$ sphere. Unlike binaural localization models trained with an HRIR catalog associated with a specific head and ear shape, an individual-agnostic model […]
Read More
Convergence between CV and NLP Modeling and Learning
Han Hu and Li Dong from Microsoft Research Asia talk about the convergence between computer vision, natural language processing, and machine learning in the following talk.
Read More
Visual Recognition beyond Appearances, and its Robotic Applications
The goal of Computer Vision, as coined by Marr, is to develop algorithms to answer What are Where at When from visual appearance. Yezhou Yang, among others, recognizes the importance of studying underlying entities and relations beyond visual appearance, following an Active Perception paradigm. This talk will present the speaker’s efforts over the last decade. […]
Read More
Tightly Connecting Vision and Language
Remarkable progress has been made at the intersection of vision and language. While showing great promise, current vision and language models may only weakly “connect” the two modalities and often fail in the wild. In this talk, Goggle’s Soravit Changpinyo will present recent efforts aiming to bridge this gap along two dimensions: informativeness and controllability. […]
Read More
Dependable IoT- Making data from IoT Devices Dependable and Trustworthy
The Internet of Things has been around for a while now and many businesses and organizations now depend on data from these systems to make critical decisions. At the same time, it is also well recognized that this data- even up to 40% of it- can be spurious, and this obviously can have a tremendously […]
Read More
Introducing Retiarii: A deep learning exploratory-training framework on NNI
Traditional deep learning frameworks such as TensorFlow and PyTorch support training on a single deep neural network (DNN) model, which involves computing the weights iteratively for the DNN model. Designing a DNN model for a task remains an experimental science and is typically a practice of deep learning model exploration. Retrofitting such exploratory-training into the […]
Read More