In this article we propose a hybrid architecture for end-to-end training of deep neural networks for event-based pattern recognition and object detection, combining a spiking neural network (SNN) backbone for efficient event-based feature extraction, and a subsequent analog neural network (ANN) head to solve synchronous classification and detection tasks.
The focus of this article is to learn deep radar spectra classifiers which offer robust real-time uncertainty estimates using label smoothing during training.
Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar. In addition to high accuracy, it is crucial for decision making in autonomous vehicles to evaluate the reliability of the predictions; however, decisions of DL networks are non-transparent.
The widespread use of Deep Learning (DL) applications in science and industry has created a large demand for efficient inference systems.
The goal of this paper is to resolve the identified issues of HB in order to provide calibrated confidence estimates using only a small holdout calibration dataset for bin optimization while preserving multi-class ranking accuracy.
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.
Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis.
Data-driven approaches to sequence-to-sequence modelling have been successfully applied to short text summarization of news articles.
Deep convolutional neural networks (CNNs) have shown great potential for numerous real-world machine learning applications, but performing inference in large CNNs in real-time remains a challenge.
Despite their advantages in terms of computational resources, latency, and power consumption, event-based implementations of neural networks have not been able to achieve the same performance figures as their equivalent state-of-the-art deep network models.
In psychophysical experiments, we evaluated human observers' skills in predicting actions from video sequences of different length, depicting the hand movement in the preparation and execution of actions before and after contact with the object.
Deep spiking neural networks (SNNs) hold great potential for improving the latency and energy efficiency of deep neural networks through event-based computation.
The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency.
no code implementations • 1 Mar 2016 • Korsuk Sirinukunwattana, Josien P. W. Pluim, Hao Chen, Xiaojuan Qi, Pheng-Ann Heng, Yun Bo Guo, Li Yang Wang, Bogdan J. Matuszewski, Elia Bruni, Urko Sanchez, Anton Böhm, Olaf Ronneberger, Bassem Ben Cheikh, Daniel Racoceanu, Philipp Kainz, Michael Pfeiffer, Martin Urschler, David R. J. Snead, Nasir M. Rajpoot
Colorectal adenocarcinoma originating in intestinal glandular structures is the most common form of colon cancer.
Segmentation of histopathology sections is an ubiquitous requirement in digital pathology and due to the large variability of biological tissue, machine learning techniques have shown superior performance over standard image processing methods.
We show here that STDP, in conjunction with a stochastic soft winner-take-all (WTA) circuit, induces spiking neurons to generate through their synaptic weights implicit internal models for subclasses (or causes") of the high-dimensional spike patterns of hundreds of pre-synaptic neurons.
Uncertainty is omnipresent when we perceive or interact with our environment, and the Bayesian framework provides computational methods for dealing with it.