Improving Self-Organizing Maps with Unsupervised Feature Extraction

• URL: http://arxiv.org/abs/2009.02174v1
• Date: Fri, 4 Sep 2020 13:19:24 GMT
• Title: Improving Self-Organizing Maps with Unsupervised Feature Extraction
• Authors: Lyes Khacef, Laurent Rodriguez, Benoit Miramond
• Abstract summary: The Self-Organizing Map (SOM) is a brain-inspired neural model that is very promising for unsupervised learning. We propose in this work to improve the SOM performance by using extracted features instead of raw data. We improve the SOM classification by +6.09% and reach state-of-the-art performance on unsupervised image classification.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Self-Organizing Map (SOM) is a brain-inspired neural model that is very promising for unsupervised learning, especially in embedded applications. However, it is unable to learn efficient prototypes when dealing with complex datasets. We propose in this work to improve the SOM performance by using extracted features instead of raw data. We conduct a comparative study on the SOM classification accuracy with unsupervised feature extraction using two different approaches: a machine learning approach with Sparse Convolutional Auto-Encoders using gradient-based learning, and a neuroscience approach with Spiking Neural Networks using Spike Timing Dependant Plasticity learning. The SOM is trained on the extracted features, then very few labeled samples are used to label the neurons with their corresponding class. We investigate the impact of the feature maps, the SOM size and the labeled subset size on the classification accuracy using the different feature extraction methods. We improve the SOM classification by +6.09\% and reach state-of-the-art performance on unsupervised image classification.

Related papers

• DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers [34.282971510732736]
  We introduce DiTMoS, a novel DNN training and inference framework with a selector-classifiers architecture. A composition of weak models can exhibit high diversity and the union of them can significantly boost the accuracy upper bound. We deploy DiTMoS on the Neucleo STM32F767ZI board and evaluate it based on three time-series datasets for human activity recognition, keywords spotting, and emotion recognition.
  arXiv  Detail & Related papers  (2024-03-14T02:11:38Z)
• Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
  Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is. This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
  arXiv  Detail & Related papers  (2024-01-18T08:12:23Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning [53.00683059396803]
  Mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images. We propose a decision-based MIM that utilizes reinforcement learning (RL) to automatically search for optimal image masking ratio and masking strategy. Our approach has a significant advantage over alternative self-supervised methods on the task of neuron segmentation.
  arXiv  Detail & Related papers  (2023-10-06T10:40:46Z)
• Automated Feature Extraction on AsMap for Emotion Classification using EEG [0.0]
  The asymmetry in the different brain regions are captured in a 2-D vector, termed as AsMap from the differential entropy (DE) features of EEG signals. AsMaps are then used to extract features automatically using Convolutional Neural Network (CNN) model. Highest classification accuracy of 97.10% is achieved on 3-class classification problem using SEED dataset.
  arXiv  Detail & Related papers  (2022-01-28T11:38:29Z)
• Dendritic Self-Organizing Maps for Continual Learning [0.0]
  We propose a novel algorithm inspired by biological neurons, termed Dendritic-Self-Organizing Map (DendSOM) DendSOM consists of a single layer of SOMs, which extract patterns from specific regions of the input space. It outperforms classical SOMs and several state-of-the-art continual learning algorithms on benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-18T14:47:19Z)
• DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer [22.46523830554047]
  We propose a Deep learning-based weak label learning method for analyzing whole slide images (WSIs) of Hematoxylin and Eosin stained tumor tissue. We apply DeepSMILE to the task of Homologous recombination deficiency (HRD) and microsatellite instability (MSI) prediction.
  arXiv  Detail & Related papers  (2021-07-20T11:00:16Z)
• Semi-Automatic Data Annotation guided by Feature Space Projection [117.9296191012968]
  We present a semi-automatic data annotation approach based on suitable feature space projection and semi-supervised label estimation. We validate our method on the popular MNIST dataset and on images of human intestinal parasites with and without fecal impurities. Our results demonstrate the added-value of visual analytics tools that combine complementary abilities of humans and machines for more effective machine learning.
  arXiv  Detail & Related papers  (2020-07-27T17:03:50Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)
• A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow [0.0]
  unsupervised learning technique of spike timing dependent plasticity (STDP) using binary activations are used to extract features from spiking input data. The accuracies obtained for the balanced EMNIST data set compare favorably with other approaches.
  arXiv  Detail & Related papers  (2020-02-26T23:47:35Z)
• Learning Class Regularized Features for Action Recognition [68.90994813947405]
  We introduce a novel method named Class Regularization that performs class-based regularization of layer activations. We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1.8%, 1.2% and 1.4% on the Kinetics, UCF-101 and HMDB-51 datasets, respectively.
  arXiv  Detail & Related papers  (2020-02-07T07:27:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.