scholarly journals Determining the accuracy in image supervised classification problems

2011 ◽  
Author(s):  
Daniel Gomez ◽  
Javier Montero
Keyword(s):  
Supervised Classification ◽  
Classification Problems

Semi-Supervised Learning

2011 ◽  
pp. 1022-1027
Author(s):  
Tobias Scheffer
Keyword(s):  
Supervised Learning ◽  
Supervised Classification ◽  
Unlabeled Data ◽  
Training Data ◽  
Classification Algorithms ◽  
Classification Problems

For many classification problems, unlabeled training data are inexpensive and readily available, whereas labeling training data imposes costs. Semi-supervised classification algorithms aim at utilizing information contained in unlabeled data in addition to the (few) labeled data.

AN ALGORITHM FOR COMPUTING TYPICAL TESTORS BASED ON ELIMINATION OF GAPS AND REDUCTION OF COLUMNS

2013 ◽  
Vol 27 (08) ◽  
pp. 1350022 ◽  
Author(s):  
ALEXSEY LIAS-RODRÍGUEZ ◽  
GUILLERMO SANCHEZ-DIAZ
Keyword(s):  
Feature Selection ◽  
Supervised Classification ◽  
State Of The Art ◽  
Experimental Results ◽  
Classification Problems ◽  
Fast Implementation ◽  
The Matrix ◽  
Feature Relevance ◽  
Exponential Complexity

Typical testors are useful tools for feature selection and for determining feature relevance in supervised classification problems. Nowadays, computing all typical testors of a training matrix is very expensive; all reported algorithms have exponential complexity depending on the number of columns in the matrix. In this paper, we introduce the faster algorithm BR (Boolean Recursive), called fast-BR algorithm, that is based on elimination of gaps and reduction of columns. Fast-BR algorithm is designed to generate all typical testors from a training matrix, requiring a reduced number of operations. Experimental results using this fast implementation and the comparison with other state-of-the-art related algorithms that generate typical testors are presented.

Feature selection using localized generalization error for supervised classification problems using RBFNN

2008 ◽  
Vol 41 (12) ◽  
pp. 3706-3719 ◽  
Author(s):  
Wing W.Y. Ng ◽  
Daniel S. Yeung ◽  
Michael Firth ◽  
Eric C.C. Tsang ◽  
Xi-Zhao Wang
Keyword(s):  
Feature Selection ◽  
Supervised Classification ◽  
Generalization Error ◽  
Classification Problems ◽  
Localized Generalization Error

scholarly journals Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6661
Author(s):  
Lars Schmarje ◽  
Johannes Brünger ◽  
Monty Santarossa ◽  
Simon-Martin Schröder ◽  
Rainer Kiko ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Supervised Classification ◽  
Limited Information ◽  
Classification Problems ◽  
Previous State ◽  
Supervised Methods ◽  
Real World Datasets ◽  
Fuzzy Labels

Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large and consistently labeled datasets. Although current approaches in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even more, this line of research still uses distinct classes. For underwater classification, and uncurated real-world datasets in general, clean class boundaries can often not be given due to a limited information content in the images and transitional stages of the depicted objects. This leads to different experts having different opinions and thus producing fuzzy labels which could also be considered ambiguous or divergent. We propose a novel framework for handling semi-supervised classifications of such fuzzy labels. It is based on the idea of overclustering to detect substructures in these fuzzy labels. We propose a novel loss to improve the overclustering capability of our framework and show the benefit of overclustering for fuzzy labels. We show that our framework is superior to previous state-of-the-art semi-supervised methods when applied to real-world plankton data with fuzzy labels. Moreover, we acquire 5 to 10% more consistent predictions of substructures.

scholarly journals Árboles de decisión para la evaluación del riesgo biológico de procesos biofarmacéuticos. //Decision trees for the biological risk assessment in biopharmaceutical processes.

Ciencia Unemi ◽  
2018 ◽  
Vol 11 (28) ◽  
pp. 8-17
Author(s):  
Pavel Novoa-Hernández ◽  
Dailín Cobos-Valdes ◽  
Eduardo Samaniego-Mena ◽  
Milvio Novoa-Pérez
Keyword(s):  
Risk Assessment ◽  
Decision Trees ◽  
Supervised Classification ◽  
Assessment Process ◽  
Classification Models ◽  
Classification Problems ◽  
Biological Risk ◽  
New Model ◽  
Pharmaceutical Processes

En el presente trabajo se propone un nuevo modelo para la evaluación del riesgo biológico en procesos biofarmacéuticos. La propuesta extiende un modelo existente, aportando como principal novedad el tratamiento de las determinaciones de los niveles de consecuencia y probabilidad de riesgo, como problemas de clasificación supervisada. Específicamente, se obtuvieron modelos de clasificación basados en árboles de decisión que poseen como ventajas más importantes: 1) un número menor de indicadores para la determinación de consecuencias y probabilidades, 2) un orden de medición de los indicadores, basado en la importancia de los mismos. Con el objetivo de analizar las bondades del nuevo modelo, se consideraron tres casos de estudio relacionados con procesos farmacéuticos reales. En comparación con el modelo anterior, el nuevo ofrece resultados similares, pero facilitando notablemente el proceso de evaluación del riesgo biológico. AbstractA new model for assessing biological risk in biopharmaceutical process is proposed in the present work. This proposal extends an existing model including the handling of the consequence and probability levels computations as main novelty, and also as supervised classification problems. Specifically, two classification models based on decision trees were obtained, which gives as major advantages: 1) a lower number of indicators for the determination of consequence and probabilities, and 2) an order of measurement of the related indicators. In order to analyze the benefits of the new model, three real pharmaceutical processes were considered as cases studies. In comparison with the previous model, the new one offers similar results, but significantly facilitating the biological risk assessment process.

scholarly journals Learning Without Feedback: Fixed Random Learning Signals Allow for Feedforward Training of Deep Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Charlotte Frenkel ◽  
Martin Lefebvre ◽  
David Bol
Keyword(s):  
Supervised Classification ◽  
Low Cost ◽  
Computational Cost ◽  
Random Projections ◽  
Smart Sensors ◽  
Classification Problems ◽  
Network Training ◽  
Memory Accesses ◽  
The One ◽  
Target Projection

While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of low-cost adaptive smart sensors at the edge, as they severely constrain memory accesses and entail buffering overhead. In this work, we show that the one-hot-encoded labels provided in supervised classification problems, denoted as targets, can be viewed as a proxy for the error sign. Therefore, their fixed random projections enable a layerwise feedforward training of the hidden layers, thus solving the weight transport and update locking problems while relaxing the computational and memory requirements. Based on these observations, we propose the direct random target projection (DRTP) algorithm and demonstrate that it provides a tradeoff between accuracy and computational cost that is suitable for adaptive edge computing devices.

A Comparative Analysis of a Novel Anomaly Detection Algorithm with Neural Networks

2020 ◽  
pp. 52-68
Author(s):  
Srijan Das ◽  
Arpita Dutta ◽  
Saurav Sharma ◽  
Sangharatna Godboley
Keyword(s):  
Neural Networks ◽  
Comparative Analysis ◽  
Anomaly Detection ◽  
Supervised Classification ◽  
Detection Algorithm ◽  
Classification Problems ◽  
Anomalous Data ◽  
Criterion Functions ◽  
The Neural Networks ◽  
Data Objects

Anomaly Detection is an important research domain of Pattern Recognition due to its effects of classification and clustering problems. In this paper, an anomaly detection algorithm is proposed using different primitive cost functions such as Normal Perceptron, Relaxation Criterion, Mean Square Error (MSE) and Ho-Kashyap. These criterion functions are minimized to locate the decision boundary in the data space so as to classify the normal data objects and the anomalous data objects. The authors proposed algorithm uses the concept of supervised classification, though it is very different from solving normal supervised classification problems. This proposed algorithm using different criterion functions has been compared with the accuracy of the Neural Networks (NN) in order to bring out a comparative analysis between them and discuss some advantages.

Sign in / Sign up

Export Citation Format

Share Document