A Hybrid Approach Based on Self-Organizing Neural Networks and the K-Nearest Neighbors Method to Study Molecular Similarity

2011 ◽  
Vol 1 (1) ◽  
pp. 75-95 ◽  
Author(s):  
Abdelmalek Amine ◽  
Zakaria Elberrichi ◽  
Michel Simonet ◽  
Ali Rahmouni
Keyword(s):  
Neural Networks ◽  
Molecular Similarity ◽  
Learning Algorithm ◽  
Hybrid Approach ◽  
Structural Similarity ◽  
Biological Properties ◽  
Learning Tools ◽  
K Nearest Neighbors ◽  
Virtual Chemical Libraries ◽  
Self Organizing

The “Molecular Similarity Principle” states that structurally similar molecules tend to have similar properties—physicochemical and biological. The question then is how to define “structural similarity” algorithmically and confirm its usefulness. Within this framework, research by similarity is registered, which is a practical approach to identify molecule candidates (to become drugs or medicines) from databases or virtual chemical libraries by comparing the compounds two by two. Many statistical models and learning tools have been developed to correlate the molecules’ structure with their chemical, physical or biological properties. The role of data mining in chemistry is to evaluate “hidden” information in a set of chemical data. Each molecule is represented by a vector of great dimension (using molecular descriptors), the applying a learning algorithm on these vectors. In this paper, the authors study the molecular similarity using a hybrid approach based on Self-Organizing Neural Networks and Knn Method.

A Hybrid Approach Based on Self-Organizing Neural Networks and the K-Nearest Neighbors Method to Study Molecular Similarity

2013 ◽  
pp. 74-95
Author(s):  
Abdelmalek Amine ◽  
Zakaria Elberrichi ◽  
Michel Simonet ◽  
Ali Rahmouni
Keyword(s):  
Neural Networks ◽  
Molecular Similarity ◽  
Learning Algorithm ◽  
Hybrid Approach ◽  
Structural Similarity ◽  
Biological Properties ◽  
Learning Tools ◽  
K Nearest Neighbors ◽  
Virtual Chemical Libraries ◽  
Self Organizing

The “Molecular Similarity Principle” states that structurally similar molecules tend to have similar properties—physicochemical and biological. The question then is how to define “structural similarity” algorithmically and confirm its usefulness. Within this framework, research by similarity is registered, which is a practical approach to identify molecule candidates (to become drugs or medicines) from databases or virtual chemical libraries by comparing the compounds two by two. Many statistical models and learning tools have been developed to correlate the molecules’ structure with their chemical, physical or biological properties. The role of data mining in chemistry is to evaluate “hidden” information in a set of chemical data. Each molecule is represented by a vector of great dimension (using molecular descriptors), the applying a learning algorithm on these vectors. In this paper, the authors study the molecular similarity using a hybrid approach based on Self-Organizing Neural Networks and Knn Method.

A Hybrid Approach Based on Self-Organizing Neural Networks and the K-Nearest Neighbors Method to Study Molecular Similarity

Data Mining ◽  
2013 ◽  
pp. 2208-2229
Author(s):  
Abdelmalek Amine ◽  
Zakaria Elberrichi ◽  
Michel Simonet ◽  
Ali Rahmouni
Keyword(s):  
Neural Networks ◽  
Molecular Similarity ◽  
Learning Algorithm ◽  
Hybrid Approach ◽  
Structural Similarity ◽  
Biological Properties ◽  
Learning Tools ◽  
K Nearest Neighbors ◽  
Virtual Chemical Libraries ◽  
Self Organizing

The “Molecular Similarity Principle” states that structurally similar molecules tend to have similar properties—physicochemical and biological. The question then is how to define “structural similarity” algorithmically and confirm its usefulness. Within this framework, research by similarity is registered, which is a practical approach to identify molecule candidates (to become drugs or medicines) from databases or virtual chemical libraries by comparing the compounds two by two. Many statistical models and learning tools have been developed to correlate the molecules’ structure with their chemical, physical or biological properties. The role of data mining in chemistry is to evaluate “hidden” information in a set of chemical data. Each molecule is represented by a vector of great dimension (using molecular descriptors), the applying a learning algorithm on these vectors. In this paper, the authors study the molecular similarity using a hybrid approach based on Self-Organizing Neural Networks and Knn Method.

Molecular Similarity

2011 ◽  
pp. 139-150
Author(s):  
Abdelmalek Amine ◽  
Zakaria Elberrichi ◽  
Michel Simonet ◽  
Ali Rahmouni
Keyword(s):  
Nearest Neighbor ◽  
New Technologies ◽  
Molecular Similarity ◽  
Learning Algorithm ◽  
Pharmaceutical Research ◽  
Biological Properties ◽  
Learning Tools ◽  
Self Organizing Maps ◽  
Kohonen Networks ◽  
Virtual Chemical Libraries

In order to identify new molecules susceptible to become medicines, the pharmaceutical research has more and more resort to new technologies to synthesize big number of molecules simultaneously and to test their actions on given therapeutic target. This data can be exploited to construct the models permitting to predict the properties of molecules not yet tested, even not yet synthesized. Such predictive models are very important because they make it possible to suggest the synthesis of new molecules, and to eliminate very early in the the molecule’s search process the molecules whose properties would prevent their use as medicine. The authors call it virtual sifting. It is within this framework that research by similarity is registered. It is a practical approach to identify molecules candidates (to become medicines) from the data bases or the virtual chemical libraries by comparing the compounds two by two. Many statistical models and learning tools have been developed to correlate the molecule’s structure with their chemical, physical or biological properties. The large majority of these methods start by transforming each molecule in a vector of great dimension (using molecular descriptors), then use a learning algorithm on these vectorial descriptions. The objective of this chapter is to study molecular similarity using a particular type of neural networks: the Kohonen networks (also called “SOM” Self- Organizing Maps), applying the nearest neighbor algorithm to the projection of the molecules (coordinates) in the constructed MAP.

scholarly journals Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors

2018 ◽  
Vol 8 (11) ◽  
pp. 2086 ◽  
Author(s):  
Antonio-Javier Gallego ◽  
Antonio Pertusa ◽  
Jorge Calvo-Zaragoza
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Nearest Neighbor ◽  
Hybrid Approach ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Neural Codes ◽  
K Nearest Neighbors ◽  
Network Topologies ◽  
Common Technique

We present a hybrid approach to improve the accuracy of Convolutional Neural Networks (CNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (kNN) algorithm for inference. Although this is a common technique in transfer learning, we apply it to the same domain for which the network was trained. Previous works show that neural codes (neuron activations of the last hidden layers) can benefit from the inclusion of classifiers such as support vector machines or random forests. In this work, our proposed hybrid CNN + kNN architecture is evaluated using several image datasets, network topologies and label noise levels. The results show significant accuracy improvements in the inference stage with respect to the standard CNN with noisy labels, especially with relatively large datasets such as CIFAR100. We also verify that applying the ℓ 2 norm on neural codes is statistically beneficial for this approach.

AN ONLINE SELF-ORGANIZING SCHEME FOR PARSIMONIOUS AND ACCURATE FUZZY NEURAL NETWORKS

2010 ◽  
Vol 20 (05) ◽  
pp. 389-403 ◽  
Author(s):  
NING WANG ◽  
MENG JOO ER ◽  
XIAN-YAO MENG ◽  
XIANG LI
Keyword(s):  
Neural Networks ◽  
High Performance ◽  
Structure Learning ◽  
Learning Algorithm ◽  
Optimal Parameter ◽  
Fuzzy Neural Networks ◽  
Benchmark Problems ◽  
Parameter Learning ◽  
Fuzzy Neural ◽  
Self Organizing

In this paper, an online self-organizing scheme for Parsimonious and Accurate Fuzzy Neural Networks (PAFNN), and a novel structure learning algorithm incorporating a pruning strategy into novel growth criteria are presented. The proposed growing procedure without pruning not only simplifies the online learning process but also facilitates the formation of a more parsimonious fuzzy neural network. By virtue of optimal parameter identification, high performance and accuracy can be obtained. The learning phase of the PAFNN involves two stages, namely structure learning and parameter learning. In structure learning, the PAFNN starts with no hidden neurons and parsimoniously generates new hidden units according to the proposed growth criteria as learning proceeds. In parameter learning, parameters in premises and consequents of fuzzy rules, regardless of whether they are newly created or already in existence, are updated by the extended Kalman filter (EKF) method and the linear least squares (LLS) algorithm, respectively. This parameter adjustment paradigm enables optimization of parameters in each learning epoch so that high performance can be achieved. The effectiveness and superiority of the PAFNN paradigm are demonstrated by comparing the proposed method with state-of-the-art methods. Simulation results on various benchmark problems in the areas of function approximation, nonlinear dynamic system identification and chaotic time-series prediction demonstrate that the proposed PAFNN algorithm can achieve more parsimonious network structure, higher approximation accuracy and better generalization simultaneously.

Review of Pattern Recognition by Self-Organizing Neural Networks.

1995 ◽  
Vol 40 (11) ◽  
pp. 1110-1110
Author(s):  
Stephen James Thomas
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Self Organizing

Study of the operation of an artificial neural network that works in the electric network in order to prevent emergency conditions.

2020 ◽  
Vol 14 (1) ◽  
pp. 48-54
Author(s):  
D. Ostrenko ◽  
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Electricity Consumption ◽  
Electrical Energy ◽  
Energy System ◽  
Electrical Networks ◽  
Electric Networks ◽  
Electric Network ◽  
Time Dynamics ◽  
Emergency Situations

Emergency modes in electrical networks, arising for various reasons, lead to a break in the transmission of electrical energy on the way from the generating facility to the consumer. In most cases, such time breaks are unacceptable (the degree depends on the class of the consumer). Therefore, an effective solution is to both deal with the consequences, use emergency input of the reserve, and prevent these emergency situations by predicting events in the electric network. After analyzing the source [1], it was concluded that there are several methods for performing the forecast of emergency situations in electric networks. It can be: technical analysis, operational data processing (or online analytical processing), nonlinear regression methods. However, it is neural networks that have received the greatest application for solving these tasks. In this paper, we analyze existing neural networks used to predict processes in electrical systems, analyze the learning algorithm, and propose a new method for using neural networks to predict in electrical networks. Prognostication in electrical engineering plays a key role in shaping the balance of electricity in the grid, influencing the choice of mode parameters and estimated electrical loads. The balance of generation of electricity is the basis of technological stability of the energy system, its violation affects the quality of electricity (there are frequency and voltage jumps in the network), which reduces the efficiency of the equipment. Also, the correct forecast allows to ensure the optimal load distribution between the objects of the grid. According to the experience of [2], different methods are usually used for forecasting electricity consumption and building customer profiles, usually based on the analysis of the time dynamics of electricity consumption and its factors, the identification of statistical relationships between features and the construction of models.

Dynamic Niche-Based Self-Organizing Learning Algorithm

2011 ◽  
Vol 22 (8) ◽  
pp. 1738-1748 ◽  
Author(s):  
Chuan-Hua ZHOU ◽  
An-Shi XIE
Keyword(s):  
Learning Algorithm ◽  
Self Organizing
Sign in / Sign up

Export Citation Format

Share Document