Supervised online diarization with sample mean loss for multi-domain data

4 Nov 20192 code implementations

Recently, a fully supervised speaker diarization approach was proposed (UIS-RNN) which models speakers using multiple instances of a parameter-sharing recurrent neural network.


On the Complexity of Exploration in Goal-Driven Navigation

16 Nov 20181 code implementation

Next, we propose to measure the complexity of each environment by constructing dependency graphs between the goals and analytically computing \emph{hitting times} of a random walk in the graph.

You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery

24 May 20182 code implementations

We further explore resolution and object size requirements by systematically testing the pipeline at decreasing resolution, and conclude that objects only ~5 pixels in size can still be localized with high confidence.


Perturbative Neural Networks

CVPR 2018 3 code implementations

Convolutional neural networks are witnessing wide adoption in computer vision systems with numerous applications across a range of visual recognition tasks.

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

CVPR 2019 3 code implementations

In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data.


An IoT Endpoint System-on-Chip for Secure and Energy-Efficient Near-Sensor Analytics

18 Dec 20163 code implementations

Near-sensor data analytics is a promising direction for IoT endpoints, as it minimizes energy spent on communication and reduces network load - but it also poses security concerns, as valuable data is stored or sent over the network at various stages of the analytics pipeline.


Neural Tangents: Fast and Easy Infinite Neural Networks in Python

5 Dec 20191 code implementation

Neural Tangents is a library designed to enable research into infinite-width neural networks.


Scalable Methods for 8-bit Training of Neural Networks

NeurIPS 2018 4 code implementations

Armed with this knowledge, we quantize the model parameters, activations and layer gradients to 8-bit, leaving at a higher precision only the final step in the computation of the weight gradients.


Guided evolutionary strategies: Augmenting random search with surrogate gradients

ICLR 2019 2 code implementations

We propose Guided Evolutionary Strategies, a method for optimally using surrogate gradient directions along with random search.


Collective Mind, Part II: Towards Performance- and Cost-Aware Software Engineering as a Natural Science

20 Jun 201525 code implementations

Nowadays, engineers have to develop software often without even knowing which hardware it will eventually run on in numerous mobile phones, tablets, desktops, laptops, data centers, supercomputers and cloud services.