Simon Kornblith

Simon Kornblith

Auto-generated profile, based on publicly available information

Simon Kornblith

Google research

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2019
Verified
Conference Paper
Closed access
SKSimon Kornblith
Simon Kornblith
JSJonathon Shlens
Jonathon Shlens
QLQuoc V. Le
Quoc V. Le
Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in modern computer vision research is that models that perform better on ImageNet necessarily perform better on other vision tasks. However, this hypothesis has never been systematically tested. Here, we compare the performance of 16 classification networks on 12 image classification datasets. We find that, when networks are used as fixed feature extractors or fine-tuned, there is a strong correlation between ImageNet accuracy and transfer accuracy (r = 0.99 and 0.96, respectively). In the former setting, we find that this relationship is very sensitive to the way in which networks are trained on ImageNet; many common forms of regularization slightly improve ImageNet accuracy but yield features that are much worse for transfer learning. Additionally, we find that, on two small fine-grained image classification datasets, pretraining on ImageNet provides minimal benefits, indicating the learned features from ImageNet do not transfer well to fine-grained tasks. Together, our results show that ImageNet architectures generalize well across datasets, but ImageNet features are less general than previously suggested.

22 February 2024 in NEJM AI
Verified
Journal Article
Closed access
TTTao Tu
Tao Tu
SAShekoofeh Azizi
Shekoofeh Azizi
DDDanny Driess
Danny Driess
MSMike Schaekermann
Mike Schaekermann
MAMohamed Amin
Mohamed Amin
VNVivek Natarajan
Vivek Natarajan

16 January 2018 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
PDF file
ABAndré M. Bastos
André M. Bastos
RLRoman Loonis
Roman Loonis
SKSimon Kornblith
Simon Kornblith
MLMikael Lundqvist
Mikael Lundqvist
EMEarl K. Miller
Earl K. Miller
Significance: The anatomy and dynamics of different layers of the cerebral cortex are distinct. Physiological work in the sensory cortex has investigated how different layers process sensory inputs, and how they are engaged during attention tasks. In the frontal and prefrontal cortices, where lamination is present, very few studies have investigated the role of distinct layers for cognition. We studied frontal cortex laminar neuronal activity as monkeys performed working memory tasks. Spiking and gamma-band activity (50–150 Hz) in the superficial layers reflected active maintenance of working memories. Alpha/beta frequencies (4–22 Hz) in the deep layers modulated the gamma activity in the superficial layers. This might serve a control function, allowing information to enter or exit active storage in superficial layers.

3 September 2008 in The Journal of Neuroscience
Verified
Journal Article
Open access
PDF file
FMFlorian Mormann
Florian Mormann
SKSimon Kornblith
Simon Kornblith
RQRodrigo Quian Quiroga
Rodrigo Quian Quiroga
AKAlexander Kraskov
Alexander Kraskov
MCMoran Cerf
Moran Cerf
CKChristof Koch
Christof Koch
Neurons in the temporal lobe of both monkeys and humans show selective responses to classes of visual stimuli and even to specific individuals. In this study, we investigate the latency and selectivity of visually responsive neurons recorded from microelectrodes in the parahippocampal cortex, entorhinal cortex, hippocampus, and amygdala of human subjects during a visual object presentation task. During 96 experimental sessions in 35 subjects, we recorded from a total of 3278 neurons. Of these units, 398 responded selectively to one or more of the presented stimuli. Mean response latencies were substantially larger than those reported in monkeys. We observed a highly significant correlation between the latency and the selectivity of these neurons: the longer the latency the greater the selectivity. Particularly, parahippocampal neurons were found to respond significantly earlier and less selectively than those in the other three regions. Regional analysis showed significant correlations between latency and selectivity within the parahippocampal cortex, entorhinal cortex, and hippocampus, but not within the amygdala. The later and more selective responses tended to be generated by cells with sparse baseline firing rates and vice versa. Our results provide direct evidence for hierarchical processing of sensory information at the interface between the visual pathway and the limbic system, by which increasingly refined and specific representations of stimulus identity are generated over time along the anatomic pathways of the medial temporal lobe.

25 July 2013 in Neuron
Verified
Journal Article
Closed access
PDF file
SKSimon Kornblith
Simon Kornblith
XCXueqi Cheng
Xueqi Cheng
SOShay Ohayon
Shay Ohayon
DTDoris Y. Tsao
Doris Y. Tsao

28 August 2011 in Nature Neuroscience
Verified
Journal Article
Closed access
PDF file
FMFlorian Mormann
Florian Mormann
JDJulien Dubois
Julien Dubois
SKSimon Kornblith
Simon Kornblith
MMMilica Milosavljevic
Milica Milosavljevic
MCMoran Cerf
Moran Cerf
CKChristof Koch
Christof Koch