Lidars and cameras are two essential sensors for perception and scene understanding. They build an environment in tandem and provide a means for detection and localisation of other objects, giving robots rich semantic information required for safe navigation. Many researchers have started exploring multi-modal deep learning model for precise 3D object detection. An interesting example would be an algorithm developed by Aptiv, PointPainting[1] Camera outperforms LIDAR when it comes to capturing denser and richer representation. From fig 2, looking at the sparse point cloud alone, it is relatively difficult to correctly identify the black box as a pedestrian.

Sign in to report inappropriate content.

Fighting fake news has become a growing problem in the past few years, and one that begs for a solution involving artificial intelligence. Verifying the near-infinite amount of content being generated on news websites, video streaming services, blogs, social media, etc. is virtually impossible There has been a push to use machine learning in the moderation of online content, but those efforts have only had modest success in finding spam and removing adult content, and to a much lesser extent detecting hate speech. Fighting fake news is a much more complicated challenge. But they have limited reach. It would be unreasonable to expect current artificial intelligence technologies to fully automate the fight against fake news.

Can the mind connect directly with artificial intelligence, robots and other minds through brain-computer interface (BCI) technologies to transcend our human limitations? For some, it is a necessity to our survival. Indeed, we would need to become cyborgs to be relevant in an artificial intelligence age. Brain-Computer Interface (BCI): devices that enable its users to interact with computers by mean of brain-activity only, this activity being generally measured by ElectroEncephaloGraphy (EEG). Electroencephalography (EEG): physiological method of choice to record the electrical activity generated by the brain via electrodes placed on the scalp surface. Functional magnetic resonance imaging (fMRI): measures brain activity by detecting changes associated with blood flow.

Data Download LJSpeech provided by keithito. It contains 13100 short audio clips of a single speaker. The total length is approximately 24 hrs. All the samples can be found here. These samples are generated after 102k updates.

Google, this week, has launched a new version of their TensorFlow framework -- TensorFlow Quantum (TFQ), which is an open-source library for prototyping quantum machine learning models. Quantum computers aren't mainstream yet; however, when they do arrive, they will need algorithms. So, TFQ will bridge that gap and will make it possible for developers/users to create hybrid AI algorithms combining both traditional and quantum computing techniques. TFQ, a smart amalgamation of TensorFlow and Cinq, will allow users to build deep learning models to run on a future quantum computer with minimal lines of Python. According to the Google AI blog post, TFQ has been designed to provide the necessary tools to bring in the techniques of quantum computing and machine learning research communities together in order to build and control natural and artificial quantum systems. The purpose of quantum computing is to aid and extend the abilities of traditional computing.

There are hundreds of blog posts on machine learning and deep learning projects, and I've learned a lot from the ones that I've read. I wanted to add to this body of knowledge by discussing a deep learning side project that I worked on recently. I've shared the project code in a Github repo. Cloud detection in satellite images is an important classification problem. It's used heavily in the field of Remote Sensing, because clouds obscure the land underneath, and too many cloudy images in a dataset make it harder for a model to learn meaningful patterns.

As billions of personal data such as photos are shared through social media and network, the privacy and security of data have drawn an increasing attention. Several attempts have been made to alleviate the leakage of identity information with the aid of image obfuscation techniques. However, most of the present results are either perceptually unsatisfactory or ineffective against real-world recognition systems. In this paper, we argue that an algorithm for privacy protection must block the ability of automatic inference of the identity and at the same time, make the resultant image natural from the users' point of view. To achieve this, we propose a targeted identity-protection iterative method (TIP-IM), which can generate natural face images by adding adversarial identity masks to conceal ones' identity against a recognition system. Extensive experiments on various state-of-the-art face recognition models demonstrate the effectiveness of our proposed method on alleviating the identity leakage of face images, without sacrificing the visual quality of the protected images.

We present a significantly-improved data-driven global weather forecasting framework using a deep convolutional neural network (CNN) to forecast several basic atmospheric variables on a global grid. New developments in this framework include an offline volume-conservative mapping to a cubed-sphere grid, improvements to the CNN architecture, and the minimization of the loss function over multiple steps in a prediction sequence. The cubed-sphere remapping minimizes the distortion on the cube faces on which convolution operations are performed and provides natural boundary conditions for padding in the CNN. Our improved model produces weather forecasts that are indefinitely stable and produce realistic weather patterns at lead times of several weeks and longer. For short- to medium-range forecasting, our model significantly outperforms persistence, climatology, and a coarse-resolution dynamical numerical weather prediction (NWP) model. Unsurprisingly, our forecasts are worse than those from a high-resolution state-of-the-art operational NWP system. Our data-driven model is able to learn to forecast complex surface temperature patterns from few input atmospheric state variables. On annual time scales, our model produces a realistic seasonal cycle driven solely by the prescribed variation in top-of-atmosphere solar forcing. Although it is currently less accurate than operational weather forecasting models, our data-driven CNN executes much faster than those models, suggesting that machine learning could prove to be a valuable tool for large-ensemble forecasting.

Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc anomaly detection techniques to detect (and discard) these anomalous samples have been proposed in the recent past. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications. We provide a taxonomy for existing techniques based on their underlying assumptions and adopted approaches. We discuss various techniques in each of the categories and provide the relative strengths and weaknesses of the approaches. Our goal in this survey is to provide an easier yet better understanding of the techniques belonging to different categories in which research has been done on this topic. Finally, we highlight the unsolved research challenges while applying anomaly detection techniques in DL systems and present some high-impact future research directions.