It is not the best of times for self-driving car startups. The past year has seen large tech companies acquire startups that were running out of cash and ride-hailing companies shutter costly self-driving car projects with no prospect of becoming production-ready anytime soon. Yet, in the midst of this downturn, Waabi, a Toronto-based self-driving car startup, has just come out of stealth with an insane amount of $83.5 million in a Series A funding round led by Khosla Ventures, with additional participation from Uber, 8VC, Radical Ventures, OMERS Ventures, BDC, and Aurora Innovation. The company's financial backers also include Geoffrey Hinton, Fei-Fei Li, Peter Abbeel, and Sanja Fidler, artificial intelligence scientists with great influence in the academia and applied AI community. What makes Waabi qualified for such support?

An advanced artificial intelligence technique known as deep learning can predict major adverse cardiac events more accurately than current standard imaging protocols, according to research presented at the Society of Nuclear Medicine and Molecular Imaging 2021 Annual Meeting. Utilizing data from a registry of more than 20,000 patients, researchers developed a novel deep learning network that has the potential to provide patients with an individualized prediction of their annualized risk for adverse events such as heart attack or death. Deep learning is a subset of artificial intelligence that mimics the workings of the human brain to process data. Deep learning algorithms use multiple layers of "neurons," or non-linear processing units, to learn representations and identify latent features relevant to a specific task, making sense of multiple types of data. It can be used for tasks such as predicting cardiovascular disease and segmenting lungs, among others.

Are you overwhelmed by the vast array of X-formers? X-formers are the name being given to the wide array of Transformer variants that have been implemented or proposed. You likely know Transformers from their recent spate of success stories in natural language processing, computer vision, and other areas of artificial intelligence, but are familiar with all of the X-formers? More importantly, do you know the differences, and why you might use one over another? A Survey of Transformers, by Tianyang Lin, Yuxin Wang, Xiangyang Liu, and Xipeng Qiu, has been written to help interested readers in this regard.

Studies on manufacturing cost prediction based on deep learning have begun in recent years, but the cost prediction rationale cannot be explained because the models are still used as a black box. This study aims to propose a manufacturing cost prediction process for 3D computer-aided design (CAD) models using explainable artificial intelligence. The proposed process can visualize the machining features of the 3D CAD model that are influencing the increase in manufacturing costs. The proposed process consists of (1) data collection and pre-processing, (2) 3D deep learning architecture exploration, and (3) visualization to explain the prediction results. The proposed deep learning model shows high predictability of manufacturing cost for the computer numerical control (CNC) machined parts. In particular, using 3D gradient-weighted class activation mapping proves that the proposed model not only can detect the CNC machining features but also can differentiate the machining difficulty for the same feature. Using the proposed process, we can provide a design guidance to engineering designers in reducing manufacturing costs during the conceptual design phase. We can also provide real-time quotations and redesign proposals to online manufacturing platform customers.

Operations in many essential industries including finance and banking are often characterized by the need to perform repetitive sequential tasks. Despite their criticality to the business, workflows are rarely fully automated or even formally specified, though there may exist a number of natural language documents describing these procedures for the employees of the company. Plan extraction methods provide us with the possibility of extracting structure plans from such natural language descriptions of the plans/workflows, which could then be leveraged by an automated system. In this paper, we investigate the utility of generalized language models in performing such extractions directly from such texts. Such models have already been shown to be quite effective in multiple translation tasks, and our initial results seem to point to their effectiveness also in the context of plan extractions. Particularly, we show that GPT-3 is able to generate plan extraction results that are comparable to many of the current state of the art plan extraction methods.

This paper presents our research on leveraging social media Big Data and AI to support hurricane disaster emergency response. The current practice of hurricane emergency response for rescue highly relies on emergency call centres. The more recent Hurricane Harvey event reveals the limitations of the current systems. We use Hurricane Harvey and the associated Houston flooding as the motivating scenario to conduct research and develop a prototype as a proof-of-concept of using an intelligent agent as a complementary role to support emergency centres in hurricane emergency response. This intelligent agent is used to collect real-time streaming tweets during a natural disaster event, to identify tweets requesting rescue, to extract key information such as address and associated geocode, and to visualize the extracted information in an interactive map in decision supports. Our experiment shows promising outcomes and the potential application of the research in support of hurricane emergency response.

In the speaker extraction problem, it is found that additional information from the target speaker contributes to the tracking and extraction of the target speaker, which includes voiceprint, lip movement, facial expression, and spatial information. However, no one cares for the cue of sound onset, which has been emphasized in the auditory scene analysis and psychology. Inspired by it, we explicitly modeled the onset cue and verified the effectiveness in the speaker extraction task. We further extended to the onset/offset cues and got performance improvement. From the perspective of tasks, our onset/offset-based model completes the composite task, a complementary combination of speaker extraction and speaker-dependent voice activity detection. We also combined voiceprint with onset/offset cues. Voiceprint models voice characteristics of the target while onset/offset models the start/end information of the speech. From the perspective of auditory scene analysis, the combination of two perception cues can promote the integrity of the auditory object. The experiment results are also close to state-of-the-art performance, using nearly half of the parameters. We hope that this work will inspire communities of speech processing and psychology, and contribute to communication between them. Our code will be available in https://github.com/aispeech-lab/wase/.

The device used in this work detects the objects over the surface of the water using two thermal cameras which aid the users to detect and avoid the objects in scenarios where the human eyes cannot (night, fog, etc.). To avoid the obstacle collision autonomously, it is required to track the objects in real-time and assign a specific identity to each object to determine its dynamics (trajectory, velocity, etc.) for making estimated collision predictions. In the following work, a Machine Learning (ML) approach for Computer Vision (CV) called Convolutional Neural Network (CNN) was used using TensorFlow as the high-level programming environment in Python. To validate the algorithm a test set was generated using an annotation tool that was created during the work for proper evaluation. Once validated, the algorithm was deployed on the platform and tested with the sequence generated by the test boat.

Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts. However, the accuracy gains are often based on specialized model designs using additional 32-bit components. Furthermore, almost all previous BNNs use 32-bit for feature maps and the shortcuts enclosing the corresponding binary convolution blocks, which helps to effectively maintain the accuracy, but is not friendly to hardware accelerators with limited memory, energy, and computing resources. Thus, we raise the following question: How can accuracy and energy consumption be balanced in a BNN network design? We extensively study this fundamental problem in this work and propose a novel BNN architecture without most commonly used 32-bit components: \textit{BoolNet}. Experimental results on ImageNet demonstrate that BoolNet can achieve 4.6x energy reduction coupled with 1.2\% higher accuracy than the commonly used BNN architecture Bi-RealNet. Code and trained models are available at: https://github.com/hpi-xnor/BoolNet.

Given high-dimensional time series data (e.g., sensor data), how can we detect anomalous events, such as system faults and attacks? More challengingly, how can we do this in a way that captures complex inter-sensor relationships, and detects and explains anomalies which deviate from these relationships? Recently, deep learning approaches have enabled improvements in anomaly detection in high-dimensional datasets; however, existing methods do not explicitly learn the structure of existing relationships between variables, or use them to predict the expected behavior of time series. Our approach combines a structure learning approach with graph neural networks, additionally using attention weights to provide explainability for the detected anomalies. Experiments on two real-world sensor datasets with ground truth anomalies show that our method detects anomalies more accurately than baseline approaches, accurately captures correlations between sensors, and allows users to deduce the root cause of a detected anomaly.