Pieter-Jan Kindermans

is this you? claim profile

0 followers
Google ∙ Berlin Institute of Technology (Technische Universität Berlin)

Discovering Multi-Hardware Mobile Models via Architecture Search

Developing efficient models for mobile phones or other on-device deploym...
08/18/2020 ∙ by Grace Chu, et al. ∙ 0 ∙ share

read it
Can weight sharing outperform random architecture search? An investigation with TuNAS

Efficient Neural Architecture Search methods based on weight sharing hav...
08/13/2020 ∙ by Gabriel Bender, et al. ∙ 15 ∙ share

read it
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

Inverted bottleneck layers, which are built upon depthwise convolutions,...
04/30/2020 ∙ by Yunyang Xiong, et al. ∙ 15 ∙ share

read it
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models

Neural architecture search (NAS) has shown promising results discovering...
03/24/2020 ∙ by Jiahui Yu, et al. ∙ 6 ∙ share

read it
Neural Predictor for Neural Architecture Search

Neural Architecture Search methods are effective but often use complex a...
12/02/2019 ∙ by Wei Wen, et al. ∙ 0 ∙ share

read it
iNNvestigate neural networks!

In recent years, deep neural networks have revolutionized many applicati...
08/13/2018 ∙ by Maximilian Alber, et al. ∙ 0 ∙ share

read it
Backprop Evolution

The back-propagation algorithm is the cornerstone of deep learning. Desp...
08/08/2018 ∙ by Maximilian Alber, et al. ∙ 4 ∙ share

read it
Evaluating Feature Importance Estimates

Estimating the influence of a given feature to a model prediction is cha...
06/28/2018 ∙ by Sara Hooker, et al. ∙ 4 ∙ share

read it
The (Un)reliability of saliency methods

Saliency methods aim to explain the predictions of deep neural networks....
11/02/2017 ∙ by Pieter-Jan Kindermans, et al. ∙ 0 ∙ share

read it
Don't Decay the Learning Rate, Increase the Batch Size

It is common practice to decay the learning rate. Here we show one can u...
11/01/2017 ∙ by Samuel L. Smith, et al. ∙ 0 ∙ share

read it
SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Deep learning has the potential to revolutionize quantum chemistry as it...
06/26/2017 ∙ by Kristof T. Schütt, et al. ∙ 0 ∙ share

read it
Learning how to explain neural networks: PatternNet and PatternAttribution

DeConvNet, Guided BackProp, LRP, were invented to better understand deep...
05/16/2017 ∙ by Pieter-Jan Kindermans, et al. ∙ 0 ∙ share

read it

Pieter-Jan Kindermans

Featured Co-authors

Klaus-Robert Müller

Quoc V. Le

Yiran Chen

Wojciech Samek

Bo Chen

Hai Li

Thomas Huang

Vikas Singh

Ruoming Pang

Been Kim

Dumitru Erhan

Discovering Multi-Hardware Mobile Models via Architecture Search

Can weight sharing outperform random architecture search? An investigation with TuNAS

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models

Neural Predictor for Neural Architecture Search

iNNvestigate neural networks!

Backprop Evolution

Evaluating Feature Importance Estimates

The (Un)reliability of saliency methods

Don't Decay the Learning Rate, Increase the Batch Size

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Learning how to explain neural networks: PatternNet and PatternAttribution