Geometric embeddings have recently received attention for their natural ability to represent transitive asymmetric relations via containment. Box embeddings, where objects are represented by n-dimensional hyperrectangles, are a particularly promising example of such an embedding as they are closed under intersection and their volume can be calculated easily, allowing them to naturally represent calibrated probability distributions. The benefits of geometric embeddings also introduce a problem of local identifiability, however, where whole neighborhoods of parameters result in equivalent loss which impedes learning. Prior work addressed some of these issues by using an approximation to Gaussian convolution over the box parameters, however, this intersection operation also increases the sparsity of the gradient. In this work, we model the box parameters with min and max Gumbel distributions, which were chosen such that space is still closed under the operation of the intersection. The calculation of the expected intersection volume involves all parameters, and we demonstrate experimentally that this drastically improves the ability of such models to learn.

Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for edge-computing. In this paper, we show that these seemingly unrelated techniques conflict with each other as network compression deforms the produced attributions, which could lead to dire consequences for mission-critical applications. This phenomenon arises due to the fact that conventional network compression methods only preserve the predictions of the network while ignoring the quality of the attributions. To combat the attribution inconsistency problem, we present a framework that can preserve the attributions while compressing a network. By employing the Weighted Collapsed Attribution Matching regularizer, we match the attribution maps of the network being compressed to its pre-compression former self. We demonstrate the effectiveness of our algorithm both quantitatively and qualitatively on diverse compression methods.

In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or requirements such as verifiable safety guarantees, it may not be feasible to actually use such high-performing DNNs in practice. Many techniques have been developed in recent years to compress or distill complex DNNs into smaller, faster or more understandable models and controllers. This work seeks to provide a quantitative framework with metrics to systematically evaluate the outcome of such conversion processes, and identify reduced models that not only preserve a desired performance level, but also, for example, succinctly explain the latent knowledge represented by a DNN. We illustrate the effectiveness of the proposed approach on the evaluation of decision tree variants in the context of benchmark reinforcement learning tasks.

To train deep learning models for vision-based action recognition of elders' daily activities, we need large-scale activity datasets acquired under various daily living environments and conditions. However, most public datasets used in human action recognition either differ from or have limited coverage of elders' activities in many aspects, making it challenging to recognize elders' daily activities well by only utilizing existing datasets. Recently, such limitations of available datasets have actively been compensated by generating synthetic data from realistic simulation environments and using those data to train deep learning models. In this paper, based on these ideas we develop ElderSim, an action simulation platform that can generate synthetic data on elders' daily activities. For 55 kinds of frequent daily activities of the elders, ElderSim generates realistic motions of synthetic characters with various adjustable data-generating options, and provides different output modalities including RGB videos, two- and three-dimensional skeleton trajectories. We then generate KIST SynADL, a large-scale synthetic dataset of elders' activities of daily living, from ElderSim and use the data in addition to real datasets to train three state-of the-art human action recognition models. From the experiments following several newly proposed scenarios that assume different real and synthetic dataset configurations for training, we observe a noticeable performance improvement by augmenting our synthetic data. We also offer guidance with insights for the effective utilization of synthetic data to help recognize elders' daily activities.

Deep learning startup Deci today announced that it raised $9.1 million in a seed funding round led by Israel-based Emerge. According to a spokesperson, the company plans to devote the proceeds to customer acquisition efforts as it expands its Tel Aviv workforce. Machine learning deployments have historically been constrained by the size and speed of algorithms and the need for costly hardware. In fact, a report from MIT found that machine learning might be approaching computational limits. A separate Synced study estimated that the University of Washington's Grover fake news detection model cost $25,000 to train in about two weeks.

Start Today and Become an Expert in Days. Recurrent Neural Networks (RNNs), a class of neural networks, are essential in processing sequences such as sensor measurements, daily stock prices, etc. In fact, most of the sequence modelling problems on images and videos are still hard to solve without Recurrent Neural Networks. Further, RNNs are also considered to be the general form of deep learning architecture. Hence, the understanding of RNNs is crucial in all the fields of Data Science.

This article is part of Demystifying AI, a series of posts that (try to) disambiguate the jargon and myths surrounding AI. With machine learning becoming increasingly popular, one thing that has been worrying experts is the security threats the technology will entail. We are still exploring the possibilities: The breakdown of autonomous driving systems? Failure of deep learning–based biometric authentication? Meanwhile, machine learning algorithms have already found their way into critical fields such as finance, health care, and transportation, where security failures can have severe repercussion.

In the next release of adabelief-pytorch, we will modify the default of several arguments, in order to fit the needs of for general tasks such as GAN and Transformer. Please check if you specify these arguments or use the default when upgrade from version 0.0.5 to higher. AdaBelief uses a different denominator from Adam, and is orthogonal to other techniques such as recification, decoupled weight decay, weight averaging et.al. This implies when you use some techniques with Adam, to get a good result with AdaBelief you might still need those techniques. The default value epsilon 1e-8 is not a good option in many cases, will modify it later to 1e-12 or 1e-16 later. If you task needs a "non-adaptive" optimizer, which means SGD performs much better than Adam(W), such as on image recognition, you need to set a large epsilon(e.g.

A recent article in The Guardian stirred up a lot of excitement--and a little fear--on social media. The reason: The initial draft was reportedly written by GPT-3, OpenAI's new text generator. Since its beta release, GPT-3, an artificial intelligence system that takes a cue and generates text, has captivated the tech community and the media. Developers and computer scientists have been using it to write articles, website markup, and even software code. Some entrepreneurs are contemplating creating new products on GPT-3.