anchor


機械学習モデルの判断根拠の説明

#artificialintelligence

The data subject shall have the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects concerning him or her or similarly significantly affects him or her. 2. Paragraph 1 shall not apply if the decision: is necessary for entering into, or performance of, a contract between the data subject and a data controller; is authorised by Union or Member State law to which the controller is subject and which also lays down suitable measures to safeguard the data subject's rights and freedoms and legitimate interests; or is based on the data subject's explicit consent. In the cases referred to in points (a) and (c) of paragraph 2, the data controller shall implement suitable measures to safeguard the data subject's rights and freedoms and legitimate interests, at least the right to obtain human intervention on the part of the controller, to express his or her point of view and to contest the decision. Lasso Given:!", $" ℝ' ℝ) 1, 2, …, . The data subject shall have the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects concerning him or her or similarly significantly affects him or her. 2. Paragraph 1 shall not apply if the decision: is necessary for entering into, or performance of, a contract between the data subject and a data controller; is authorised by Union or Member State law to which the controller is subject and which also lays down suitable measures to safeguard the data subject's rights and freedoms and legitimate interests; or is based on the data subject's explicit consent. In the cases referred to in points (a) and (c) of paragraph 2, the data controller shall implement suitable measures to safeguard the data subject's rights and freedoms and legitimate interests, at least the right to obtain human intervention on the part of the controller, to express his or her point of view and to contest the decision.


Face Recognition – Aniket Maurya – Medium

#artificialintelligence

Face Verification checks "is this the claimed person?". For example, in school, you go with your ID card and the invigilator verifies your face with the ID card. A mobile phone that unlocks using our face is also using face verification. It is 1:1 matching problem. Now suppose the invigilator knows everyone by their name.


MetaAnchor: Learning to Detect Objects with Customized Anchors

Neural Information Processing Systems

We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnchor anchor functions could be dynamically generated from the arbitrary customized prior boxes. Taking advantage of weight prediction, MetaAnchor is able to work with most of the anchor-based object detection systems such as RetinaNet. Compared with the predefined anchor scheme, we empirically find that MetaAnchor is more robust to anchor settings and bounding box distributions; in addition, it also shows the potential on the transfer task. Our experiment on COCO detection task shows MetaAnchor consistently outperforms the counterparts in various scenarios.


The Global Anchor Method for Quantifying Linguistic Shifts and Domain Adaptation

Neural Information Processing Systems

Language is dynamic, constantly evolving and adapting with respect to time, domain or topic. The adaptability of language is an active research area, where researchers discover social, cultural and domain-specific changes in language using distributional tools such as word embeddings. In this paper, we introduce the global anchor method for detecting corpus-level language shifts. We show both theoretically and empirically that the global anchor method is equivalent to the alignment method, a widely-used method for comparing word embeddings, in terms of detecting corpus-level language shifts. Despite their equivalence in terms of detection abilities, we demonstrate that the global anchor method is superior in terms of applicability as it can compare embeddings of different dimensionalities. Furthermore, the global anchor method has implementation and parallelization advantages. We show that the global anchor method reveals fine structures in the evolution of language and domain adaptation. When combined with the graph Laplacian technique, the global anchor method recovers the evolution trajectory and domain clustering of disparate text corpora.


Five Ways China Used Facial Recognition in 2018

#artificialintelligence

Imagine a world in which you can scan your face to board a train, check into a hotel, order a meal at a café, or even track your food from farm to table. In China, all of this is already happening. Facial recognition became more pervasive this year after the Chinese government in December 2017 announced an ambitious plan to achieve greater face-reading accuracy by 2020. The country also plans to introduce a system that will identify any of its 1.3 billion citizens in just three seconds. Public and private enterprises have rushed to adopt the futuristic, artificial intelligence-powered technology, implementing facial-recognition systems in transportation networks, medical facilities, and law enforcement initiatives.


PointPillars: Fast Encoders for Object Detection from Point Clouds

arXiv.org Machine Learning

Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.


Real life 'shrink ray' can reduce 3D structures to one thousandth of their original size

Daily Mail

MIT researchers have created a real life'shrink ray' that can reduce 3D structures to one thousandth of their original size. Scientists can put all kinds of useful materials in the polymer before they shrink it, including metals, quantum dots, and DNA. The process is essentially the opposite of expansion microscopy, which is widely used by scientists to create 3D visualisations of microscopic cells. Instead of making things bigger, scientists attach special molecules which block negative charges between molecules so they no longer repel which makes them contract. Experts say that making such tiny structures could be useful in many fields, including in medicine and for creating nanoscale robotics.


The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech

arXiv.org Machine Learning

Speech datasets for identifying Alzheimer's disease (AD) are generally restricted to participants performing a single task, e.g. describing an image shown to them. As a result, models trained on linguistic features derived from such datasets may not be generalizable across tasks. Building on prior work demonstrating that same-task data of healthy participants helps improve AD detection on a single-task dataset of pathological speech, we augment an AD-specific dataset consisting of subjects describing a picture with multi-task healthy data. We demonstrate that normative data from multiple speech-based tasks helps improve AD detection by up to 9%. Visualization of decision boundaries reveals that models trained on a combination of structured picture descriptions and unstructured conversational speech have the least out-of-task error and show the most potential to generalize to multiple tasks. We analyze the impact of age of the added samples and if they affect fairness in classification. We also provide explanations for a possible inductive bias effect across tasks using model-agnostic feature anchors. This work highlights the need for heterogeneous datasets for encoding changes in multiple facets of cognition and for developing a task-independent AD detection model.


A Look Ahead: Where Artificial Intelligence May Take Journalism in 2019

#artificialintelligence

The Washington Post, Associated Press, and Reuters are just a few of the industry leaders who turned to AI in 2018. Publishers who adopted AI and machine-learning tools have seen results. Last year, Digiday reported The Washington Post's robot reporter published 850 stories in a year. Next year, the global media industry will begin to use these new tools at a faster rate. Here are a few current stories on AI that will have real implications for journalism in 2019.


Saliency Supervision: An Intuitive and Effective Approach for Pain Intensity Regression

arXiv.org Artificial Intelligence

Getting pain intensity from face images is an important problem in autonomous nursing systems. However, due to the limitation in data sources and the subjectiveness in pain intensity values, it is hard to adopt modern deep neural networks for this problem without domain-specific auxiliary design. Inspired by human vision priori, we propose a novel approach called saliency supervision, where we directly regularize deep networks to focus on facial area that is discriminative for pain regression. Through alternative training between saliency supervision and global loss, our method can learn sparse and robust features, which is proved helpful for pain intensity regression. We verified saliency supervision with face-verification network backbone on the widely-used dataset, and achieved state-of-art performance without bells and whistles. Our saliency supervision is intuitive in spirit, yet effective in performance. We believe such saliency supervision is essential in dealing with ill-posed datasets, and has potential in a wide range of vision tasks.