The Covid-19 pandemic was devastating for many industries, but it only accelerated the use of artificial intelligence across the U.S. economy. Amid the crisis, companies scrambled to create new services for remote workers and students, beef up online shopping and dining options, make customer call centers more efficient and speed development of important new drugs. Even as applications of machine learning and perception platforms become commonplace, a thick layer of hype and fuzzy jargon clings to AI-enabled software.That makes it tough to identify the most compelling companies in the space--especially those finding new ways to use AI that create value by making humans more efficient, not redundant. With this in mind, Forbes has partnered with venture firms Sequoia Capital and Meritech Capital to create our third annual AI 50, a list of private, promising North American companies that are using artificial intelligence in ways that are fundamental to their operations. To be considered, businesses must be privately-held and utilizing machine learning (where systems learn from data to improve on tasks), natural language processing (which enables programs to "understand" written or spoken language) or computer vision (which relates to how machines "see"). AI companies incubated at, largely funded through or acquired by large tech, manufacturing or industrial firms aren't eligible for consideration. Our list was compiled through a submission process open to any AI company in the U.S. and Canada. The application asked companies to provide details on their technology, business model, customers and financials like funding, valuation and revenue history (companies had the option to submit information confidentially, to encourage greater transparency). Forbes received several hundred entries, of which nearly 400 qualified for consideration. From there, our data partners applied an algorithm to identify 100 companies with the highest quantitative scores--and that also made diversity a priority. Next, a panel of expert AI judges evaluated the finalists to find the 50 most compelling companies (they were precluded from judging companies in which they have a vested interest). Among trends this year are what Sequoia Capital's Konstantine Buhler calls AI workbench companies--building of platforms tailored to different enterprises, including Dataiku, DataRobot Domino Data and Databricks.

From the Sojourner rover, which landed on Mars in 1997, to Perseverance, which touched down in February, the robots of the Red Planet share a defining feature: wheels. Rolling is far more stable and energy efficient than walking, which even robots on Earth still struggle to master. After all, NASA would hate for its very expensive Martian explorer to topple over and flail around like a turtle on its back. The problem with wheels, though, is that they limit where rovers can go: To explore complicated Martian terra like steep hills, you need the kinds of legs that evolution gave animals on Earth. So a team of scientists from ETH Zurich in Switzerland and the Max Planck Institute for Solar System Research in Germany have been playing around with a small quadrupedal robot called SpaceBok, designed to mimic an antelope known as a springbok.

… Bruhnke and Stefany Goradia, worked with RS21 to develop a platform using AI and machine learning to identify trends in health care data.

With the Deep Neural Networks (DNNs) as a powerful function approximator, Deep Reinforcement Learning (DRL) has been excellently demonstrated on robotic control tasks. Compared to DNNs with vanilla artificial neurons, the biologically plausible Spiking Neural Network (SNN) contains a diverse population of spiking neurons, making it naturally powerful on state representation with spatial and temporal information. Based on a hybrid learning framework, where a spike actor-network infers actions from states and a deep critic network evaluates the actor, we propose a Population-coding and Dynamic-neurons improved Spiking Actor Network (PDSAN) for efficient state representation from two different scales: input coding and neuronal coding. For input coding, we apply population coding with dynamically receptive fields to directly encode each input state component. For neuronal coding, we propose different types of dynamic-neurons (containing 1st-order and 2nd-order neuronal dynamics) to describe much more complex neuronal dynamics. Finally, the PDSAN is trained in conjunction with deep critic networks using the Twin Delayed Deep Deterministic policy gradient algorithm (TD3-PDSAN). Extensive experimental results show that our TD3-PDSAN model achieves better performance than state-of-the-art models on four OpenAI gym benchmark tasks. It is an important attempt to improve RL with SNN towards the effective computation satisfying biological plausibility.

A central goal of machine learning is to learn robust representations that capture the causal relationship between inputs features and output labels. However, minimizing empirical risk over finite or biased datasets often results in models latching on to spurious correlations between the training input/output pairs that are not fundamental to the problem at hand. In this paper, we define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution (i.e. covariate shift), models can still pick up spurious features from their training data. Group distributionally robust optimization (DRO) provides an effective tool to alleviate covariate shift by minimizing the worst-case training loss over a set of pre-defined groups. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations that occur in the data. To address this, we further propose to minimize the worst-case losses over a more flexible set of distributions that are defined on the joint distribution of groups and instances, instead of treating each group as a whole at optimization time. Through extensive experiments on one image and two language tasks, we show that our model is significantly more robust than comparable baselines under various partitions. Our code is available at https://github.com/violet-zct/group-conditional-DRO.

We revisit and extend model stitching (Lenc & Vedaldi 2015) as a methodology to study the internal representations of neural networks. Given two trained and frozen models $A$ and $B$, we consider a "stitched model'' formed by connecting the bottom-layers of $A$ to the top-layers of $B$, with a simple trainable layer between them. We argue that model stitching is a powerful and perhaps under-appreciated tool, which reveals aspects of representations that measures such as centered kernel alignment (CKA) cannot. Through extensive experiments, we use model stitching to obtain quantitative verifications for intuitive statements such as "good networks learn similar representations'', by demonstrating that good networks of the same architecture, but trained in very different ways (e.g.: supervised vs. self-supervised learning), can be stitched to each other without drop in performance. We also give evidence for the intuition that "more is better'' by showing that representations learnt with (1) more data, (2) bigger width, or (3) more training time can be "plugged in'' to weaker models to improve performance. Finally, our experiments reveal a new structural property of SGD which we call "stitching connectivity'', akin to mode-connectivity: typical minima reached by SGD can all be stitched to each other with minimal change in accuracy.

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.

Is Einstein more agreeable and less neurotic than Hitler? Abstract Recent progress in distributed semantic models (DSM) offers new ways to estimate personality traits of both fictive and real people. In this exploratory study we applied an extended version of the algorithm developed in Jacobs (2019) to compute the likeability scores, emotional figure profiles and BIG5 personality traits for 100 historical persons from the arts, politics or science domains whose names are rather unique (e.g., Einstein, Kahlo, Picasso). We compared the results produced by static (word2vec) and dynamic (BERT) language model representations in four studies. The results show both the potential and limitations of such DSM-based computations of personality profiles and point ways to further develop this approach to become a useful tool in data science, psychology or computational and neurocognitive poetics (Jacobs, 2015).

Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the performance of various sequence labeling tasks, their computational cost is expensive. To alleviate this problem, we extend the recent successful early-exit mechanism to accelerate the inference of PTMs for sequence labeling tasks. However, existing early-exit mechanisms are specifically designed for sequence-level tasks, rather than sequence labeling. In this paper, we first propose a simple extension of sentence-level early-exit for sequence labeling tasks. To further reduce the computational cost, we also propose a token-level early-exit mechanism that allows partial tokens to exit early at different layers. Considering the local dependency inherent in sequence labeling, we employed a window-based criterion to decide for a token whether or not to exit. The token-level early-exit brings the gap between training and inference, so we introduce an extra self-sampling fine-tuning stage to alleviate it. The extensive experiments on three popular sequence labeling tasks show that our approach can save up to 66%-75% inference cost with minimal performance degradation. Compared with competitive compressed models such as DistilBERT, our approach can achieve better performance under the same speed-up ratios of 2X, 3X, and 4X.

It is well known that modern deep neural networks are powerful enough to memorize datasets even when the labels have been randomized. Recently, Vershynin (2020) settled a long standing question by Baum (1988), proving that \emph{deep threshold} networks can memorize $n$ points in $d$ dimensions using $\widetilde{\mathcal{O}}(e^{1/\delta^2}+\sqrt{n})$ neurons and $\widetilde{\mathcal{O}}(e^{1/\delta^2}(d+\sqrt{n})+n)$ weights, where $\delta$ is the minimum distance between the points. In this work, we improve the dependence on $\delta$ from exponential to almost linear, proving that $\widetilde{\mathcal{O}}(\frac{1}{\delta}+\sqrt{n})$ neurons and $\widetilde{\mathcal{O}}(\frac{d}{\delta}+n)$ weights are sufficient. Our construction uses Gaussian random weights only in the first layer, while all the subsequent layers use binary or integer weights. We also prove new lower bounds by connecting memorization in neural networks to the purely geometric problem of separating $n$ points on a sphere using hyperplanes.