Mixed-precision quantization is a powerful tool to enable memory and compute savings of neural network workloads by deploying different sets of bit-width precisions on separate compute operations. Recent research has shown significant progress in applying mixed-precision quantization techniques to reduce the memory footprint of various workloads, while also preserving task performance. Prior work, however, has often ignored additional objectives, such as bit-operations, that are important for deployment of workloads on hardware. Here we present a flexible and scalable framework for automated mixed-precision quantization that optimizes multiple objectives. Our framework relies on Neuroevolution-Enhanced Multi-Objective Optimization (NEMO), a novel search method, to find Pareto optimal mixed-precision configurations for memory and bit-operations objectives. Within NEMO, a population is divided into structurally distinct sub-populations (species) which jointly form the Pareto frontier of solutions for the multi-objective problem. At each generation, species are re-sized in proportion to the goodness of their contribution to the Pareto frontier. This allows NEMO to leverage established search techniques and neuroevolution methods to continually improve the goodness of the Pareto frontier. In our experiments we apply a graph-based representation to describe the underlying workload, enabling us to deploy graph neural networks trained by NEMO to find Pareto optimal configurations for various workloads trained on ImageNet. Compared to the state-of-the-art, we achieve competitive results on memory compression and superior results for compute compression for MobileNet-V2, ResNet50 and ResNeXt-101-32x8d. A deeper analysis of the results obtained by NEMO also shows that both the graph representation and the species-based approach are critical in finding effective configurations for all workloads.

A few years ago, the first CNN surpassed human performance on ImageNet. However, it soon became clear that machines lack robustness on more challenging test cases, a major obstacle towards deploying machines "in the wild" and towards obtaining better computational models of human visual perception. Here we ask: Are we making progress in closing the gap between human and machine vision? To answer this question, we tested human observers on a broad range of out-of-distribution (OOD) datasets, adding the "missing human baseline" by recording 85,120 psychophysical trials across 90 participants. We then investigated a range of promising machine learning developments that crucially deviate from standard supervised CNNs along three axes: objective function (self-supervised, adversarially trained, CLIP language-image training), architecture (e.g. vision transformers), and dataset size (ranging from 1M to 1B). Our findings are threefold. (1.) The longstanding robustness gap between humans and CNNs is closing, with the best models now matching or exceeding human performance on most OOD datasets. (2.) There is still a substantial image-level consistency gap, meaning that humans make different errors than models. In contrast, most models systematically agree in their categorisation errors, even substantially different ones like contrastive self-supervised vs. standard supervised models. (3.) In many cases, human-to-model consistency improves when training dataset size is increased by one to three orders of magnitude. Our results give reason for cautious optimism: While there is still much room for improvement, the behavioural difference between human and machine vision is narrowing. In order to measure future progress, 17 OOD datasets with image-level human behavioural data are provided as a benchmark here: https://github.com/bethgelab/model-vs-human/

Adeva partners with companies to scale engineering teams on-demand. AgentFire - Hyper local real estate websites powered by Wordpress. Aha! - Aha! is roadmapping software for PMs who want their mojo back. AirTreks - Multi-stop international flight planner with a distributed team. We are strategists, researchers, designers, and developers who craft custom digital experiences for publishers, nonprofit institutions, museums, and brands. ALICE empowers the world's best hotels to deliver a remarkable guest experience. Makes software that helps teachers make e-learning courses. AT&T - Nearly 20% of the eligible workforce works remotely. Authentic F & F - Independent design and technology studio based in Denver and Minnesota Aurity - 100% remote company, specializing in React and React Native.

The graph represents a network of 2,921 Twitter users whose tweets in the requested range contained "#FinServ", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Sunday, 13 June 2021 at 01:33 UTC. The requested start date was Sunday, 13 June 2021 at 00:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 7,500. The tweets in the network were tweeted over the 12-day, 9-hour, 51-minute period from Sunday, 30 May 2021 at 00:09 UTC to Friday, 11 June 2021 at 10:01 UTC.

Using drones and artificial intelligence to monitor large colonies of seabirds can be as effective as traditional on-the-ground methods, while reducing costs, labor and the risk of human error, a new study finds. Scientists at Duke University and the Wildlife Conservation Society (WCS) used a deep-learning algorithm--a form of artificial intelligence--to analyze more than 10,000 drone images of mixed colonies of seabirds in the Falkland Islands off Argentina's coast. The Falklands, also known as the Malvinas, are home to the world's largest colonies of black-browed albatrosses (Thalassarche melanophris) and second-largest colonies of southern rockhopper penguins (Eudyptes c. chrysocome). Hundreds of thousands of birds breed on the islands in densely interspersed groups. The deep-learning algorithm correctly identified and counted the albatrosses with 97% accuracy and the penguins with 87%.

Small Robot Company (SRC), a British agritech startup for sustainable farming, has developed AI-enabled robots – named Tom, Dick and Harry – that identify and kill individual weeds with electricity. These agricultural robots could reduce the use of harmful chemicals and heavy machinery, paving the way for a new approach to sustainable crop farming. The startup has been working on automated weed killers since 2017, and this April officially launched Tom, the first commercial robot currently operating on three UK farms. Dick is still in the prototype phase, and Harry is still in development. Small Robot company says the robot Tom is capable of scanning around 20 Hectares per day, collecting about six terabytes of data in an 8-hour shift to identify the crops, spots undesirable weeds – using "Wilma," an artificial intelligence operating system.

The United Nations Educational, Scientific, and Cultural Organization (UNESCO) today unveiled its latest Science Report. The massive undertaking -- this year's report totals 762 pages, compiled by 70 authors from 52 countries over 18 months -- is published every five years to examine current trends in science governance. This latest edition includes discussion of the rapid progress toward Industry 4.0 and, for the first time, a deep analysis of AI and robotics research around the globe. Going beyond just the global leaders, it offers an overview of almost two dozen countries and global regions, examining AI research, funding, strategies, and more. Overall, the report determines "it is the field of AI and robotics that dominated scientific output" in recent years.

In the summer of 2009, the Israeli neuroscientist Henry Markram strode onto the TED stage in Oxford, England, and made an immodest proposal: Within a decade, he said, he and his colleagues would build a complete simulation of the human brain inside a supercomputer. They'd already spent years mapping the cells in the neocortex, the supposed seat of thought and perception. "It's a bit like going and cataloging a piece of the rain forest," Markram explained. "How many trees does it have? What shapes are the trees?"

With the popularity of Machine Learning (ML) solutions, algorithms and data have been released faster than the capacity of processing them. In this context, the problem of Algorithm Recommendation (AR) is receiving a significant deal of attention recently. This problem has been addressed in the literature as a learning task, often as a Meta-Learning problem where the aim is to recommend the best alternative for a specific dataset. For such, datasets encoded by meta-features are explored by ML algorithms that try to learn the mapping between meta-representations and the best technique to be used. One of the challenges for the successful use of ML is to define which features are the most valuable for a specific dataset since several meta-features can be used, which increases the meta-feature dimension. This paper presents an empirical analysis of Feature Selection and Feature Extraction in the meta-level for the AR problem. The present study was focused on three criteria: predictive performance, dimensionality reduction, and pipeline runtime. As we verified, applying Dimensionality Reduction (DR) methods did not improve predictive performances in general. However, DR solutions reduced about 80% of the meta-features, obtaining pretty much the same performance as the original setup but with lower runtimes. The only exception was PCA, which presented about the same runtime as the original meta-features. Experimental results also showed that various datasets have many non-informative meta-features and that it is possible to obtain high predictive performance using around 20% of the original meta-features. Therefore, due to their natural trend for high dimensionality, DR methods should be used for Meta-Feature Selection and Meta-Feature Extraction.

We develop a novel method for carrying out model selection for Bayesian autoencoders (BAEs) by means of prior hyper-parameter optimization. Inspired by the common practice of type-II maximum likelihood optimization and its equivalence to Kullback-Leibler divergence minimization, we propose to optimize the distributional sliced-Wasserstein distance (DSWD) between the output of the autoencoder and the empirical data distribution. The advantages of this formulation are that we can estimate the DSWD based on samples and handle high-dimensional problems. We carry out posterior estimation of the BAE parameters via stochastic gradient Hamiltonian Monte Carlo and turn our BAE into a generative model by fitting a flexible Dirichlet mixture model in the latent space. Consequently, we obtain a powerful alternative to variational autoencoders, which are the preferred choice in modern applications of autoencoders for representation learning with uncertainty. We evaluate our approach qualitatively and quantitatively using a vast experimental campaign on a number of unsupervised learning tasks and show that, in small-data regimes where priors matter, our approach provides state-of-the-art results, outperforming multiple competitive baselines.