A biologically-inspired approach to biomedical image segmentation
Ciampi L., Lagani G., Amato G., Falchi F.
We present a novel bio-inspired semi-supervised learning strategy for semantic segmentation architectures. It is based on the so-called Hebbian principle “neurons that fire together wire together” that closely mimics brain synaptic adaptations and provides a promising biologically-plausible local learning rule for updating neural network weights without needing supervision. Our approach includes two stages. In the first step, we exploit the Hebbian principle for unsupervised weights updating of both convolutional and, for the first time, transpose-convolutional layers characterizing downsampling-upsampling semantic segmentation architectures. Then, in the second stage, we fine-tune the model on a few labeled data samples. We assess our methodology through an experimental evaluation involving several collections of biomedical images, deeming that this context is of outstanding importance in computer vision and is particularly affected by data scarcity. Preliminary results demonstrate the effectiveness of our proposed method compared with SOTA under various labeled training data regimes. The code to reproduce our experiments is available at: https://tinyurl.com/ycywfjc2.Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 15636, pp. 158-171. Milan, Italy, September 29–October 4, 2024, 29/09-04/10/2024
DOI: 10.1007/978-3-031-91578-9_10
Project(s): SUN , Tuscany Health Ecosystem
Metrics:

See at: doi.org | CNR IRIS | CNR IRIS | link.springer.com

2025 Conference article Open Access

CA3D: Convolutional-Attentional 3D nets for efficient video activity recognition on the edge
Lagani G., Falchi F., Gennaro C., Amato G.
In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attention mechanism. Moreover, we introduce a novel quantization mechanism to further improve the efficiency of our model during both training and inference. Our model maintains a reduced computational cost, while preserving robust learning and generalization capabilities. Our approach addresses the issues related to the high computing requirements of current models, with the goal of achieving competitive accuracy on consumer and edge devices, enabling smart home and smart healthcare applications where efficiency and privacy issues are of concern. We experimentally validate our model on different established and publicly available video activity recognition benchmarks, improving accuracy over alternative models at a competitive computing cost.Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 15633, pp. 235-251. Milan, Italy, 29/09/2024
DOI: 10.1007/978-3-031-91979-4_18
DOI: 10.48550/arxiv.2505.19928
Project(s): AI4Media , SUN
Metrics:

See at: arXiv.org e-Print Archive | CNR IRIS | link.springer.com | doi.org | doi.org | CNR IRIS | CNR IRIS

2024 Other Open Access

See at: CNR IRIS | CNR IRIS

2024 Journal article Open Access

See at: CNR IRIS | www.sciencedirect.com | CNR IRIS | CNR IRIS

See at: CNR IRIS | CNR IRIS

See at: CNR IRIS | CNR IRIS

2023 Conference article Open Access

See at: ceur-ws.org | CNR IRIS | ISTI Repository | CNR IRIS

2023 Other Open Access

See at: CNR IRIS | ISTI Repository | CNR IRIS

2023 Other Open Access

See at: CNR IRIS | CNR IRIS

2022 Journal article Open Access

Comparing the performance of Hebbian against backpropagation learning using convolutional neural networks
Lagani G, Falchi F, Gennaro C, Amato G
In this paper, we investigate Hebbian learning strategies applied to Convolutional Neural Network (CNN) training. We consider two unsupervised learning approaches, Hebbian Winner-Takes-All (HWTA), and Hebbian Principal Component Analysis (HPCA). The Hebbian learning rules are used to train the layers of a CNN in order to extract features that are then used for classification, without requiring backpropagation (backprop). Experimental comparisons are made with state-of-the-art unsupervised (but backprop-based) Variational Auto-Encoder (VAE) training. For completeness,we consider two supervised Hebbian learning variants (Supervised Hebbian Classifiers--SHC, and Contrastive Hebbian Learning--CHL), for training the final classification layer, which are compared to Stochastic Gradient Descent training. We also investigate hybrid learning methodologies, where some network layers are trained following the Hebbian approach, and others are trained by backprop. We tested our approaches on MNIST, CIFAR10, and CIFAR100 datasets. Our results suggest that Hebbian learning is generally suitable for training early feature extraction layers, or to retrain higher network layers in fewer training epochs than backprop. Moreover, our experiments show that Hebbian learning outperforms VAE training, with HPCA performing generally better than HWTA.Source: NEURAL COMPUTING & APPLICATIONS
DOI: 10.1007/s00521-021-06701-4
Project(s): AI4EU , AI4Media
Metrics:

See at: CNR IRIS | link.springer.com | ISTI Repository | ISTI Repository | CNR IRIS | CNR IRIS | CNR IRIS

2022 Other Open Access

See at: CNR IRIS | ISTI Repository | CNR IRIS

2022 Conference article Open Access

FastHebb: scaling hebbian training of deep neural networks to ImageNet level
Lagani G, Gennaro C, Fassold H, Amato G
Learning algorithms for Deep Neural Networks are typically based on supervised end-to-end Stochastic Gradient Descent (SGD) training with error backpropagation (backprop). Backprop algorithms require a large number of labelled training samples to achieve high performance. However, in many realistic applications, even if there is plenty of image samples, very few of them are labelled, and semi-supervised sample-efficient training strategies have to be used. Hebbian learning represents a possible approach towards sample efficient training; however, in current solutions, it does not scale well to large datasets. In this paper, we present FastHebb, an efficient and scalable solution for Hebbian learning which achieves higher efficiency by 1) merging together update computation and aggregation over a batch of inputs, and 2) leveraging efficient matrix multiplication algorithms on GPU. We validate our approach on different computer vision benchmarks, in a semi-supervised learning scenario. FastHebb outperforms previous solutions by up to 50 times in terms of training speed, and notably, for the first time, we are able to bring Hebbian algorithms to ImageNet scale.DOI: 10.1007/978-3-031-17849-8_20
Project(s): AI4Media
Metrics:

See at: CNR IRIS | link.springer.com | doi.org | CNR IRIS | CNR IRIS

2022 Conference article Open Access

Recent advancements on bio-inspired Hebbian learning for deep neural networks
Lagani G
Deep learning is becoming more and more popular to extract information from multimedia data for indexing and query processing. In recent contributions, we have explored a biologically inspired strategy for Deep Neural Network (DNN) training, based on the Hebbian principle in neuroscience. We studied hybrid approaches in which unsupervised Hebbian learning was used for a pre-training stage, followed by supervised fine-tuning based on Stochastic Gradient Descent (SGD). The resulting semi-supervised strategy exhibited encouraging results on computer vision datasets, motivating further interest towards applications in the domain of large scale multimedia content based retrieval.Source: CEUR WORKSHOP PROCEEDINGS, pp. 610-615. Pisa, Italy, 2022
Project(s): AI4EU , AI4Media

See at: ceur-ws.org | CNR IRIS | ISTI Repository | CNR IRIS

Bio-inspired approaches for Deep Learning: from spiking neural networks to Hebbian plasticity
Lagani G
In the past few years, Deep Neural Network (DNN) architectures have achieved outstanding results in several Artificial Intelligence (AI) domains. Even though DNNs draw inspiration from biology, the training methods based on the backpropagation algorithm (\textit{backprop}) lack neuroscientific plausibility. The goal of this dissertation is to explore biologically-inspired solutions for the learning task. These are interesting because they can help to reproduce features of the human brain, for example, the ability to learn from a little experience. The investigation is divided into three phases: first, I explore a novel AI solution based on simulating neuronal biological cultures with a high level of detail, using biologically faithful Spiking Neural Network (SNN) models; second, I investigate neuroscientifically grounded \textit{Hebbian} learning rules, applied to traditional DNNs in combination with backprop, using computer vision as a case study; third, I consider a more applicative perspective, using neural features derived from Hebbian learning for multimedia content retrieval tasks. I validate the proposed methods on different benchmarks, including MNIST, CIFAR, and ImageNet, obtaining promising results, especially in learning scenarios with scarce data. Moreover, to the best of my knowledge, for the first time, I am able to bring bio-inspired Hebbian methods to ImageNet scale, consisting of over 1 million images.Project(s): AI4Media

See at: etd.adm.unipi.it | CNR IRIS | CNR IRIS

2022 Conference article Open Access

Deep features for CBIR with scarce data using Hebbian learning
Lagani G., Bacciu D., Gallicchio C., Falchi F., Gennaro C., Amato G.
Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR). Recently, biologically inspired Hebbian learning algorithms have shown promises for DNN training. In this contribution, we study the performance of such algorithms in the development of feature extractors for CBIR tasks. Specifically, we consider a semi-supervised learning strategy in two steps: first, an unsupervised pre-training stage is performed using Hebbian learning on the image dataset; second, the network is fine-tuned using supervised Stochastic Gradient Descent (SGD) training. For the unsupervised pre-training stage, we explore the nonlinear Hebbian Principal Component Analysis (HPCA) learning rule. For the supervised fine-tuning stage, we assume sample efficiency scenarios, in which the amount of labeled samples is just a small fraction of the whole dataset. Our experimental analysis, conducted on the CIFAR10 and CIFAR100 datasets, shows that, when few labeled samples are available, our Hebbian approach provides relevant improvements compared to various alternative methods.DOI: 10.1145/3549555.3549587
DOI: 10.48550/arxiv.2205.08935
Project(s): AI4Media
Metrics:

See at: arXiv.org e-Print Archive | dl.acm.org | ZENODO | CNR IRIS | IRIS Cnr | doi.org | doi.org | Archivio della Ricerca - Università di Pisa | IRIS Cnr | CNR IRIS | CNR IRIS

2021 Journal article Open Access

Hebbian semi-supervised learning in a sample efficiency setting
Lagani G, Falchi F, Gennaro C, Amato G
We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both convolutional and fully connected) are pre-trained using an unsupervised approach based on Hebbian learning, and the last fully connected layer (the classification layer) is trained using Stochastic Gradient Descent (SGD). In fact, as Hebbian learning is an unsupervised learning method, its potential lies in the possibility of training the internal layers of a DCNN without labels. Only the final fully connected layer has to be trained with labeled examples. We performed experiments on various object recognition datasets, in different regimes of sample efficiency, comparing our semi-supervised (Hebbian for internal layers + SGD for the final fully connected layer) approach with end-to-end supervised backprop training, and with semi-supervised learning based on Variational Auto-Encoder (VAE). The results show that, in regimes where the number of available labeled samples is low, our semi-supervised approach outperforms the other approaches in almost all the cases.Source: NEURAL NETWORKS, vol. 143, pp. 719-731
DOI: 10.1016/j.neunet.2021.08.003
DOI: 10.48550/arxiv.2103.09002
Project(s): AI4EU , AI4Media
Metrics:

See at: arXiv.org e-Print Archive | Neural Networks | CNR IRIS | ISTI Repository | www.sciencedirect.com | ZENODO | Neural Networks | doi.org | CNR IRIS | CNR IRIS | CNR IRIS

2021 Other Open Access

See at: CNR IRIS | ISTI Repository | CNR IRIS

Hebbian Learning GitHub repository
Lagani G
Pytorch implementation of Hebbian learning algorithms to train deep convolutional neural networks.Project(s): AI4Media

See at: github.com | CNR IRIS

2021 Conference article Open Access

Assessing pattern recognition performance of neuronal cultures through accurate simulation
Lagani G, Mazziotti R, Falchi F, Gennaro C, Cicchini Gm, Pizzorusso T, Cremisi F, Amato G
Previous work has shown that it is possible to train neuronal cultures on Multi-Electrode Arrays (MEAs), to recognize very simple patterns. However, this work was mainly focused to demonstrate that it is possible to induce plasticity in cultures, rather than performing a rigorous assessment of their pattern recognition performance. In this paper, we address this gap by developing a methodology that allows us to assess the performance of neuronal cultures on a learning task. Specifically, we propose a digital model of the real cultured neuronal networks; we identify biologically plausible simulation parameters that allow us to reliably reproduce the behavior of real cultures; we use the simulated culture to perform handwritten digit recognition and rigorously evaluate its performance; we also show that it is possible to find improved simulation parameters for the specific task, which can guide the creation of real cultures.Source: INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING, pp. 726-729. Online, 4-6/05/2021
DOI: 10.1109/ner49283.2021.9441166
DOI: 10.48550/arxiv.2012.10355
Project(s): AI4Media
Metrics:

See at: arXiv.org e-Print Archive | arxiv.org | ZENODO | IRIS Cnr | IRIS Cnr | Software Heritage | Software Heritage | dblp.uni-trier.de | doi.org | doi.org | GitHub | GitHub | Flore (Florence Research Repository) | CNR IRIS | CNR IRIS

2020 Other Open Access

See at: CNR IRIS | ISTI Repository | CNR IRIS