SignificanceThe ability to complete patterns and interpret partial information is a central property of intelligence. Deep convolutional network architectures have proved successful in labeling whole objects in images and capturing the initial 150 ms of processing along the ventral visual cortex. This study shows that human object recognition abilities remain robust when only small amounts of information are available due to heavy occlusion, but the performance of bottom-up computational models is impaired under limited visibility. The results provide combined behavioral, neurophysiological, and modeling insights showing how recurrent computations may help the brain solve the fundamental challenge of pattern completion.

Summary Natural vision often involves recognizing objects from partial information. Recognition of objects from parts presents a significant challenge for theories of vision because it requires spatial integration and extrapolation from prior knowledge. Here we recorded intracranial field potentials of 113 visually selective electrodes from epilepsy patients in response to whole and partial objects. Responses along the ventral visual stream, particularly the Inferior Occipital and Fusiform Gyri, remained selective despite showing only 9–25% of the object areas. However, these visually selective signals emerged ~100 ms later for partial versus whole objects. These processing delays were particularly pronounced in higher visual areas within the ventral stream. This latency difference persisted when controlling for changes in contrast, signal amplitude, and the strength of selectivity. These results argue against a purely feed-forward explanation of recognition from partial information, and provide spatiotemporal constraints on theories of object recognition that involve recurrent processing.

Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and four orders of magnitude in performance; they range from embedded devices to data-center solutions. Fueling the hardware are a dozen or more software frameworks and libraries. The myriad combinations of ML hardware and ML software make assessing ML-system performance in an architecture-neutral, representative, and reproducible manner challenging. There is a clear need for industry-wide standard ML benchmarking and evaluation criteria. MLPerf Inference answers that call. Driven by more than 30 organizations as well as more than 200 ML engineers and practitioners, MLPerf implements a set of rules and practices to ensure comparability across systems with wildly differing architectures. In this paper, we present the method and design principles of the initial MLPerf Inference release. The first call for submissions garnered more than 600 inference-performance measurements from 14 organizations, representing over 30 systems that show a range of capabilities.

No abstract

Detection and segmentation of objects in overheard imagery is a challenging task. The variable density, random orientation, small size, and instance-to-instance heterogeneity of objects in overhead imagery calls for approaches distinct from existing models designed for natural scene datasets. Though new overhead imagery datasets are being developed, they almost universally comprise a single view taken from directly overhead ("at nadir"), failing to address a critical variable: look angle. By contrast, views vary in real-world overhead imagery, particularly in dynamic scenarios such as natural disasters where first looks are often over 40 • off-nadir. This represents an important challenge to computer vision methods, as changing view angle adds distortions, alters resolution, and changes lighting. At present, the impact of these perturbations for algorithmic detection and segmentation of objects is untested. To address this problem, we present an open source Multi-View Overhead Imagery dataset, termed SpaceNet MVOI, with 27 unique looks from a broad range of viewing angles (−32.5 • to 54.0 • ). Each of these images cover the same 665 km 2 geographic extent and are annotated with 126,747 building footprint labels, enabling direct assessment of the impact of viewpoint perturbation on model performance. We benchmark multiple leading segmentation and object detection models on: (1) building detection, (2) generalization to unseen viewing angles and resolutions, and (3) sensitivity of building footprint extraction to changes in resolution. We find that state of the art segmentation and object detection models struggle to identify buildings in off-nadir imagery and generalize poorly to unseen views, presenting an important benchmark to explore the broadly relevant challenge of detecting small, heterogeneous target objects in visually dynamic contexts.

Episodic memories are long lasting and full of detail, yet imperfect and malleable. We quantitatively evaluated recollection of short audiovisual segments from movies as a proxy to real-life memory formation in 161 subjects at 15 minutes up to a year after encoding. Memories were reproducible within and across individuals, showed the typical decay with time elapsed between encoding and testing, were fallible yet accurate, and were insensitive to low-level stimulus manipulations but sensitive to high-level stimulus properties. Remarkably, memorability was also high for single movie frames, even one year post-encoding. To evaluate what determines the efficacy of long-term memory formation, we developed an extensive set of content annotations that included actions, emotional valence, visual cues and auditory cues. These annotations enabled us to document the content properties that showed a stronger correlation with recognition memory and to build a machine-learning computational model that accounted for episodic memory formation in single events for group averages and individual subjects with an accuracy of up to 80%. These results provide initial steps towards the development of a quantitative computational theory capable of explaining the subjective filtering steps that lead to how humans learn and consolidate memories.

Whole-genome sequencing, particularly in fungi, has progressed at a tremendous rate. More difficult, however, is experimental testing of the inferences about gene function that can be drawn from comparative sequence analysis alone. We present a genome-wide functional characterization of a sequenced but experimentally understudied budding yeast, Saccharomyces bayanus var. uvarum (henceforth referred to as S. bayanus), allowing us to map changes over the 20 million years that separate this organism from S. cerevisiae. We first created a suite of genetic tools to facilitate work in S. bayanus. Next, we measured the gene-expression response of S. bayanus to a diverse set of perturbations optimized using a computational approach to cover a diverse array of functionally relevant biological responses. The resulting data set reveals that gene-expression patterns are largely conserved, but significant changes may exist in regulatory networks such as carbohydrate utilization and meiosis. In addition to regulatory changes, our approach identified gene functions that have diverged. The functions of genes in core pathways are highly conserved, but we observed many changes in which genes are involved in osmotic stress, peroxisome biogenesis, and autophagy. A surprising number of genes specific to S. bayanus respond to oxidative stress, suggesting the organism may have evolved under different selection pressures than S. cerevisiae. This work expands the scope of genome-scale evolutionary studies from sequence-based analysis to rapid experimental characterization and could be adopted for functional mapping in any lineage of interest. Furthermore, our detailed characterization of S. bayanus provides a valuable resource for comparative functional genomics studies in yeast.

Rapid and flexible interpretation of conflicting sensory inputs in the context of current goals is a critical component of cognitive control that is orchestrated by frontal cortex. The relative roles of distinct subregions within frontal cortex are poorly understood. To examine the dynamics underlying cognitive control across frontal regions, we took advantage of the spatiotemporal resolution of intracranial recordings in epilepsy patients while subjects resolved color-word conflict. We observed differential activity preceding the behavioral responses to conflict trials throughout frontal cortex; this activity was correlated with behavioral reaction times. These signals emerged first in anterior cingulate cortex (ACC) before dorsolateral prefrontal cortex (dlPFC), followed by medial frontal cortex (mFC) and then by orbitofrontal cortex (OFC). These results disassociate the frontal subregions based on their dynamics, and suggest a temporal hierarchy for cognitive control in human cortex.DOI: http://dx.doi.org/10.7554/eLife.12352.001