Channel State Information (CSI) of WiFi signals becomes increasingly attractive in human sensing applications due to the pervasiveness of WiFi, robustness to illumination and view points, and little privacy concern comparing to cameras. In majority of existing works, CSI sequences are analyzed by traditional signal processing approaches. These approaches rely on strictly imposed assumption on propagation paths, reflection and attenuation of signal interacting with human bodies and indoor background. This makes existing approaches very difficult to model the delicate body characteristics and activities in the real applications. To address these issues, we build CSI-Net, a unified Deep Neural Network (DNN), that fully utilizes the strength of deep feature representation and the power of existing DNN architectures for CSI-based human sensing problems. Using CSI-Net, we jointly solved two body characterization problems: biometrics estimation (including body fat, muscle, water and bone rates) and human identification. We also demonstrated the application of CSI-Net on two distinctive action recognition tasks: the hand sign recognition (fine-scaled action of the hand) and falling detection (coarse-scaled motion of the body). Besides the technical contribution of CSI-Net, we present major discoveries and insights on how the multi-frequency CSI signals are encoded and processed in DNNs, which, to the best of our knowledge, is the first attempt that bridges the WiFi sensing and deep learning in human sensing problems.

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disentanglement, prediction, and other metrics. Instead, we develop an unsupervised learning method that explicitly optimizes for the ability to learn a variety of tasks from small amounts of data. To do so, we construct tasks from unlabeled data in an automatic way and run meta-learning over the constructed tasks. Surprisingly, we find that, when integrated with meta-learning, relatively simple mechanisms for task design, such as clustering unsupervised representations, lead to good performance on a variety of downstream tasks. Our experiments across four image datasets indicate that our unsupervised meta-learning approach acquires a learning algorithm without any labeled data that is applicable to a wide range of downstream classification tasks, improving upon the representation learned by four prior unsupervised learning methods.

The wild success of Deep Neural Network (DNN) models in a variety of domains has created considerable excitement in the machine learning community. Despite this success, a deep understanding of why DNNs perform so well, and whether their performance is somehow brittle, has been lacking. The discovery[1] that several Deep Neural Network (DNN) models are vulnerable to adversarial examples: it is often possible to slightly perturb the input to a DNN classifier (e.g. an image-classifier) in such a way that the perturbation is invisible to a human, and yet the classifier's output can change drastically: for example a classifier that is correctly labeling an image as a school bus can be fooled into classifying it as an ostritch by adding an imperceptible change to the image. Besides the obvious security implications, the existense of adversarial examples seems to suggest that perhaps DNNs are not really learning the "essense" of a concept (which would presumably make them robust to such attacks). This opens up a variety of research avenues aimed at developing methods to train adversarially robust networks, and examining properties of adversarially trained networks.

Editors Note: We are arranging interviews with leads on both the hardware and software side of this story and will update it with more information throughout the day. We all expected that the Summit supercomputer at Oak Ridge National Lab would be a major part of pushing deep learning forward in HPC given its balanced GPU and IBM Power9 profile (not to mention the on-site expertise to get those graphics engines doing cutting-edge work outside of traditional simulations). Today, researchers from Berkeley Lab and Oak Ridge, along with development partners at Nvidia demonstrated some rather remarkable results using deep learning to extract weather patterns based on existing high-res climate simulation data. This places the collaboration in the running for this year's Gordon Bell Prize, an annual award based on high performance, efficient use of real-world applications that can scale on some of the world's most powerful supercomputers. We have written before about how deep learning could be integrated into existing weather workloads on supercomputers, but this particular piece of news captures the performance potential of integrating AI into scientific workflows.

In this context, computer vision, applied to faces, has many subareas. These include face detection, recognition, and tracking. Moreover, with the advance of Deep Learning, these solutions are getting more mature for commercial applications. This post shows you, piece-by-piece, how to design and train your own Convolutional Neural Network (CNN) for face identification. Here, we propose a Tensorflow Eager implementation of Siamese DenseNets.

Video Artificial Intelligence (AI) and Deep Learning is now being used to help schools across the U.S. rapidly and cost-effectively enhance safety and security measures in order to help prevent school shootings and other safety issues facing students on a daily basis. The program was announced recently by Deep North – a pioneer in AI and Deep Learning. A select number of schools will have the opportunity to deploy and field-test this video AI platform in a novel way, leveraging Deep North's advanced object and facial recognition technology to detect and prevent a variety of threats to student safety. The demand for sensible and cost-effective safety measures in schools continues to grow exponentially. The company, therefore, plans to expand into the education sector as a whole in the future.

Linear Algebra is a continuous form of mathematics and is applied throughout science and engineering because it allows you to model natural phenomena and to compute them efficiently. Because it is a form of continuous and not discrete mathematics, a lot of computer scientists don't have a lot of experience with it. Linear Algebra is also central to almost all areas of mathematics like geometry and functional analysis. Its concepts are a crucial prerequisite for understanding the theory behind Machine Learning, especially if you are working with Deep Learning Algorithms. You don't need to understand Linear Algebra before getting started with Machine Learning, but at some point, you may want to gain a better understanding of how the different Machine Learning algorithms really work under the hood.

Microearthquakes -- low-intensity earthquakes that register 2.0 or less magnitude on the moment magnitude scale -- rarely cause property damage. And as a result of background noise, small events, and false positives, they're not always picked up by seismic monitoring systems. A possible solution is described in a new paper from the Department of Geophysics at Stanford University, where scientists have developed an AI system -- dubbed Cnn-Rnn Earthquake Detector, or CRED -- that can isolate and identify a range of seismic signals from historical and continuous data. It builds on the work of Harvard and Google, which in August created an AI model capable of predicting the location of aftershocks up to one year after a major earthquake. The researchers' system consists of neural network layers -- interconnected processing nodes that loosely mimic the function of neurons in the brain -- of two types: convolutional neural networks and recurrent neural networks.

TensorFlow is an open-source library for numerical computation in which it uses data flow graphs. The Google Brain Team researchers developed this with the Machine Intelligence research organization by Google. TensorFlow is open source and available to the public. It is also good for distributed computing. A minimalist, modular, Neural Network library, Keras uses Theano or TensorFlow as a backend.

DeepMind is furthering its cancer research efforts with a newly announced partnership. Today, the London-based Google subsidiary said it has been given access to mammograms from roughly 30,000 women that were taken at Jikei University Hospital in Tokyo, Japan between 2007 and 2018. It'll use that data to refine its artificially intelligent (AI) breast cancer detection algorithms. Over the course of the next five years, DeepMind researchers will review the 30,000 images, along with 3,500 images from magnetic resonance imaging (MRI) scans and historical mammograms provided by the U.K.'s Optimam (an image database of over 80,000 scans extracted from the NHS' National Breast Screening System), to investigate whether its AI systems can accurately spot signs of cancerous tissue. The collaboration builds on DeepMind's work with the Cancer Research UK Imperial Center at Imperial College London, where it has already analyzed roughly 7,500 mammograms.