Learning Dendrite Morphological Neurons Using Linkage Trees for Pattern Classification

Tovias-Alanis, Samuel Omar; Gómez-Flores, Wilfrido; Toscano-Pulido, Gregorio; Azuela, Juan Humberto Sossa

doi:10.1007/978-3-031-07750-0_10

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Softmax function (SM ) is generally used as prediction function to classify a given input (decision-making) [8], [16]. Such function can be taken in the probabilistic context by means of the Bayes' theorem, considering probabilistic generative models (Naive Bayes, Bayesian networks and Hidden Markov Models) where the class-conditional densities and the prior are modeled (or known), and then the posterior probabilities can be estimated through the Bayes' theorem.…”

Section: Introductionmentioning

confidence: 99%

Reducing Overconfidence Predictions in Autonomous Driving Perception

Melotti,

Premebida,

Bird

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Object recognition is a crucial step in perception systems for autonomous and intelligent vehicles, as evidenced by the numerous research works in the topic. In this paper, object recognition is explored by using multisensory and multimodality approaches, with the intention of reducing the false positive rate (FPR). The reduction of the FPR becomes increasingly important in perception systems since the misclassification of an object can, depending on the circumstances, potentially cause accidents. In particular, this work presents a strategy through Bayesian inference to reduce the FPR considering the likelihood function as a cumulative distribution function from Gaussian kernel density estimations, and the prior probabilities as cumulative functions of normalized histograms. The validation of the proposed methodology is performed on the KITTI dataset using deep networks (DenseNet, NasNet, and EfficientNet), and recent 3D point cloud networks (PointNet, and PointNet++), by considering three object-categories (cars, cyclists, pedestrians) and the RGB and LiDAR sensor modalities.

show abstract

Section: Introductionmentioning

confidence: 99%