RESUMEN
A good theory of mathematical beauty is more practical than any current observation, as new predictions about physical reality can be self-consistently verified. This belief applies to the current status of understanding deep neural networks including large language models and even the biological intelligence. Toy models provide a metaphor of physical reality, allowing mathematically formulating the reality (i.e., the so-called theory), which can be updated as more conjectures are justified or refuted. One does not need to present all details in a model, but rather, more abstract models are constructed, as complex systems such as the brains or deep networks have many sloppy dimensions but much less stiff dimensions that strongly impact macroscopic observables. This type of bottom-up mechanistic modeling is still promising in the modern era of understanding the natural or artificial intelligence. Here, we shed light on eight challenges in developing theory of intelligence following this theoretical paradigm. Theses challenges are representation learning, generalization, adversarial robustness, continual learning, causal learning, internal model of the brain, next-token prediction, and the mechanics of subjective experience.
RESUMEN
Cognitive scientists believe that adaptable intelligent agents like humans perform spatial reasoning tasks by learned causal mental simulation. The problem of learning these simulations is called predictive world modeling. We present the first framework for a learning open-vocabulary predictive world model (OV-PWM) from sensor observations. The model is implemented through a hierarchical variational autoencoder (HVAE) capable of predicting diverse and accurate fully observed environments from accumulated partial observations. We show that the OV-PWM can model high-dimensional embedding maps of latent compositional embeddings representing sets of overlapping semantics inferable by sufficient similarity inference. The OV-PWM simplifies the prior two-stage closed-set PWM approach to the single-stage end-to-end learning method. CARLA simulator experiments show that the OV-PWM can learn compact latent representations and generate diverse and accurate worlds with fine details like road markings, achieving 69 mIoU over six query semantics on an urban evaluation sequence. We propose the OV-PWM as a versatile continual learning paradigm for providing spatio-semantic memory and learned internal simulation capabilities to future general-purpose mobile robots.
RESUMEN
OBJECTIVES: This work aims to explore the impact of multicenter data heterogeneity on deep learning brain metastases (BM) autosegmentation performance, and assess the efficacy of an incremental transfer learning technique, namely learning without forgetting (LWF), to improve model generalizability without sharing raw data. MATERIALS AND METHODS: A total of six BM datasets from University Hospital Erlangen (UKER), University Hospital Zurich (USZ), Stanford, UCSF, New York University (NYU), and BraTS Challenge 2023 were used. First, the performance of the DeepMedic network for BM autosegmentation was established for exclusive single-center training and mixed multicenter training, respectively. Subsequently privacy-preserving bilateral collaboration was evaluated, where a pretrained model is shared to another center for further training using transfer learning (TL) either with or without LWF. RESULTS: For single-center training, average F1 scores of BM detection range from 0.625 (NYU) to 0.876 (UKER) on respective single-center test data. Mixed multicenter training notably improves F1 scores at Stanford and NYU, with negligible improvement at other centers. When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0.839) than naive TL (0.570) and single-center training (0.688) on combined UKER and USZ test data. Naive TL improves sensitivity and contouring accuracy, but compromises precision. Conversely, LWF demonstrates commendable sensitivity, precision and contouring accuracy. When applied to Stanford, similar performance was observed. CONCLUSION: Data heterogeneity (e.g., variations in metastases density, spatial distribution, and image spatial resolution across centers) results in varying performance in BM autosegmentation, posing challenges to model generalizability. LWF is a promising approach to peer-to-peer privacy-preserving model training.
Asunto(s)
Neoplasias Encefálicas , Aprendizaje Profundo , Humanos , Neoplasias Encefálicas/secundario , Neoplasias Encefálicas/radioterapia , PrivacidadRESUMEN
Pre-trained models are commonly used in Continual Learning to initialize the model before training on the stream of non-stationary data. However, pre-training is rarely applied during Continual Learning. We investigate the characteristics of the Continual Pre-Training scenario, where a model is continually pre-trained on a stream of incoming data and only later fine-tuned to different downstream tasks. We introduce an evaluation protocol for Continual Pre-Training which monitors forgetting against a Forgetting Control dataset not present in the continual stream. We disentangle the impact on forgetting of 3 main factors: the input modality (NLP, Vision), the architecture type (Transformer, ResNet) and the pre-training protocol (supervised, self-supervised). Moreover, we propose a Sample-Efficient Pre-training method (SEP) that speeds up the pre-training phase. We show that the pre-training protocol is the most important factor accounting for forgetting. Surprisingly, we discovered that self-supervised continual pre-training in both NLP and Vision is sufficient to mitigate forgetting without the use of any Continual Learning strategy. Other factors, like model depth, input modality and architecture type are not as crucial.
RESUMEN
Lifelong Machine Learning (LML) denotes a scenario involving multiple sequential tasks, each accompanied by its respective dataset, in order to solve specific learning problems. In this context, the focus of LML techniques is on utilizing already acquired knowledge to adapt to new tasks efficiently. Essentially, LML concerns about facing new tasks while exploiting the knowledge previously gathered from earlier tasks not only to help in adapting to new tasks but also to enrich the understanding of past ones. By understanding this concept, one can better grasp one of the major obstacles in LML, known as Knowledge Transfer (KT). This systematic literature review aims to explore state-of-the-art KT techniques within LML and assess the evaluation metrics and commonly utilized datasets in this field, thereby keeping the LML research community updated with the latest developments. From an initial pool of 417 articles from four distinguished databases, 30 were deemed highly pertinent for the information extraction phase. The analysis recognizes four primary KT techniques: Replay, Regularization, Parameter Isolation, and Hybrid. This study delves into the characteristics of these techniques across both neural network (NN) and non-neural network (non-NN) frameworks, highlighting their distinct advantages that have captured researchers' interest. It was found that the majority of the studies focused on supervised learning within an NN modelling framework, particularly employing Parameter Isolation and Hybrid for KT. The paper concludes by pinpointing research opportunities, including investigating non-NN models for Replay and exploring applications outside of computer vision (CV).
RESUMEN
BACKGROUND: When multiple tasks are learned consecutively, the old model parameters may be overwritten by the new data, resulting in the phenomenon that the new task is learned and the old task is forgotten, which leads to catastrophic forgetting. Moreover, continual learning has no mature solution for image denoising tasks. METHODS: Therefore, in order to solve the problem of catastrophic forgetting caused by learning multiple denoising tasks, we propose a Triplet Neural-networks Collaboration-continuity DeNosing (TNCDN) model. Use triplet neural networks to update each other cooperatively. The knowledge from two denoising networks that maintain continual learning capability is transferred to the main-denoising network. The main-denoising network has new knowledge and can consolidate old knowledge. A co-training mechanism is designed. The main-denoising network updates the other two denoising networks with different thresholds to maintain memory reinforcement capability and knowledge extension capability. RESULTS: The experimental results show that our method effectively alleviates catastrophic forgetting. In GS, CT and ADNI datasets, compared with ANCL, the TNCDN(PromptIR) method reduced the average degree of forgetting on the evaluation index PSNR by 2.38 (39%) and RMSE by 1.63 (55%). CONCLUSION: This study aims to solve the problem of catastrophic forgetting caused by learning multiple denoising tasks. Although the experimental results are promising, extending the basic denoising model to more data sets and tasks will enhance its application. Nevertheless, this study is a starting point, which can provide reference and support for the further development of continuous learning image denoising task.
Asunto(s)
Redes Neurales de la Computación , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Algoritmos , Relación Señal-RuidoRESUMEN
Continual learning (CL) refers to an agent's capability to learn from a continuous stream of data and transfer knowledge without forgetting old information. One crucial aspect of CL is forward transfer, i.e., improved and faster learning on a new task by leveraging information from prior knowledge. While this ability comes naturally to biological brains, it poses a significant challenge for artificial intelligence (AI). Here, we suggest that environmental enrichment (EE) can be used as a biological model for studying forward transfer, inspiring human-like AI development. EE refers to animal studies that enhance cognitive, social, motor, and sensory stimulation and is a model for what, in humans, is referred to as 'cognitive reserve'. Enriched animals show significant improvement in learning speed and performance on new tasks, typically exhibiting forward transfer. We explore anatomical, molecular, and neuronal changes post-EE and discuss how artificial neural networks (ANNs) can be used to predict neural computation changes after enriched experiences. Finally, we provide a synergistic way of combining neuroscience and AI research that paves the path toward developing AI capable of rapid and efficient new task learning.
RESUMEN
Variable speed limit (VSL) control benefits freeway operations through dynamic speed limit adjustment strategies for specific operation scenarios, such as traffic jams, secondary crash prevention, etc. To develop optimal strategies, deep reinforcement learning (DRL) has been employed to map the traffic operation status to speed limits with the corresponding control effects. Then, VSL control strategies were obtained based upon memories of these complex mapping relationships. However, under multi-scenario conditions, DRL trained VSL faces the challenge of performance decay, where the control strategy effects drop sharply for early trained "old scenarios". This so-called scenario forgetting problem is attributed to the fact that DRL would forget the learned old scenario mapping memories after new scenario trainings. To tackle this issue, a continual learning approach has been introduced in this study to enhance the multi-scenario applicability of VSL control strategies. Specifically, a gradient projection memory (GPM) based neural network parameter updating method was proposed to keep the mapping memories of old scenarios during new scenario trainings by imposing constraints on the direction of gradient updates for new tasks. The proposed method was evaluated using three typical freeway operation scenarios developed in the simulation platform SUMO. Experimental results showed that the continual learning approach has substantially reduced the performance decay in old scenarios by 17.76% (valued using backward transfer metrics). Furthermore, the multi-scenario VSL control strategies successfully reduced the speed standard deviation and average travel time by 28.77% and 7.25% respectively. Moreover, the generalization of the proposed continual learning based VSL approach were evaluated and discussed.
Asunto(s)
Accidentes de Tránsito , Conducción de Automóvil , Humanos , Conducción de Automóvil/educación , Conducción de Automóvil/psicología , Accidentes de Tránsito/prevención & control , Aprendizaje Profundo , Redes Neurales de la Computación , Simulación por Computador , Planificación Ambiental , Refuerzo en PsicologíaRESUMEN
Electroencephalography (EEG) based Brain Computer Interface (BCI) systems play a significant role in facilitating how individuals with neurological impairments effectively interact with their environment. In real world applications of BCI system for clinical assistance and rehabilitation training, the EEG classifier often needs to learn on sequentially arriving subjects in an online manner. As patterns of EEG signals can be significantly different for different subjects, the EEG classifier can easily erase knowledge of learnt subjects after learning on later ones as it performs decoding in online streaming scenario, namely catastrophic forgetting. In this work, we tackle this problem with a memory-based approach, which considers the following conditions: (1) subjects arrive sequentially in an online manner, with no large scale dataset available for joint training beforehand, (2) data volume from the different subjects could be imbalanced, (3) decoding difficulty of the sequential streaming signal vary, (4) continual classification for a long time is required. This online sequential EEG decoding problem is more challenging than classic cross subject EEG decoding as there is no large-scale training data from the different subjects available beforehand. The proposed model keeps a small balanced memory buffer during sequential learning, with memory data dynamically selected based on joint consideration of data volume and informativeness. Furthermore, for the more general scenarios where subject identity is unknown to the EEG decoder, aka. subject agnostic scenario, we propose a kernel based subject shift detection method that identifies underlying subject changes on the fly in a computationally efficient manner. We develop challenging benchmarks of streaming EEG data from sequentially arriving subjects with both balanced and imbalanced data volumes, and performed extensive experiments with a detailed ablation study on the proposed model. The results show the effectiveness of our proposed approach, enabling the decoder to maintain performance on all previously seen subjects over a long period of sequential decoding. The model demonstrates the potential for real-world applications.
Asunto(s)
Interfaces Cerebro-Computador , Electroencefalografía , Memoria , Electroencefalografía/métodos , Humanos , Memoria/fisiología , Procesamiento de Señales Asistido por Computador , Encéfalo/fisiología , AlgoritmosRESUMEN
The aim of this work is to develop and evaluate a deep classifier that can effectively prioritize Emergency Medical Call Incidents (EMCI) according to their life-threatening level under the presence of dataset shifts. We utilized a dataset consisting of 1982746 independent EMCI instances obtained from the Health Services Department of the Region of Valencia (Spain), with a time span from 2009 to 2019 (excluding 2013). The dataset includes free text dispatcher observations recorded during the call, as well as a binary variable indicating whether the event was life-threatening. To evaluate the presence of dataset shifts, we examined prior probability shifts, covariate shifts, and concept shifts. Subsequently, we designed and implemented four deep Continual Learning (CL) strategies-cumulative learning, continual fine-tuning, experience replay, and synaptic intelligence-alongside three deep CL baselines-joint training, static approach, and single fine-tuning-based on DistilBERT models. Our results demonstrated evidence of prior probability shifts, covariate shifts, and concept shifts in the data. Applying CL techniques had a statistically significant (α=0.05) positive impact on both backward and forward knowledge transfer, as measured by the F1-score, compared to non-continual approaches. We can argue that the utilization of CL techniques in the context of EMCI is effective in adapting deep learning classifiers to changes in data distributions, thereby maintaining the stability of model performance over time. To our knowledge, this study represents the first exploration of a CL approach using real EMCI data.
Asunto(s)
Aprendizaje Profundo , Humanos , Bases de Datos Factuales , España , Servicios Médicos de UrgenciaRESUMEN
The advancements in deep learning have significantly enhanced the capability of image generation models to produce images aligned with human intentions. However, training and adapting these models to new data and tasks remain challenging because of their complexity and the risk of catastrophic forgetting. This study proposes a method for addressing these challenges involving the application of class-replacement techniques within a continual learning framework. This method utilizes selective amnesia (SA) to efficiently replace existing classes with new ones while retaining crucial information. This approach improves the model's adaptability to evolving data environments while preventing the loss of past information. We conducted a detailed evaluation of class-replacement techniques, examining their impact on the "class incremental learning" performance of models and exploring their applicability in various scenarios. The experimental results demonstrated that our proposed method could enhance the learning efficiency and long-term performance of image generation models. This study broadens the application scope of image generation technology and supports the continual improvement and adaptability of corresponding models.
RESUMEN
PURPOSE: Focal cortical dysplasias (FCDs) are a leading cause of drug-resistant epilepsy. Early detection and resection of FCDs have favorable prognostic implications for postoperative seizure freedom. Despite advancements in imaging methods, FCD detection remains challenging. House et al. (2021) introduced a convolutional neural network (CNN) for automated FCD detection and segmentation, achieving a sensitivity of 77.8%. However, its clinical applicability was limited due to a low specificity of 5.5%. The objective of this study was to improve the CNN's performance through data-driven training and algorithm optimization, followed by a prospective validation on daily-routine MRIs. MATERIAL AND METHODS: A dataset of 300 3â¯T MRIs from daily clinical practice, including 3D T1 and FLAIR sequences, was prospectively compiled. The MRIs were visually evaluated by two neuroradiologists and underwent morphometric assessment by two epileptologists. The dataset included 30 FCD cases (11 female, mean age: 28.1 ± 10.1 years) and a control group of 150 normal cases (97 female, mean age: 32.8 ± 14.9 years), along with 120 non-FCD pathological cases (64 female, mean age: 38.4 ± 18.4 years). The dataset was divided into three subsets, each analyzed by the CNN. Subsequently, the CNN underwent a two-phase-training process, incorporating subset MRIs and expert-labeled FCD maps. This training employed both classical and continual learning techniques. The CNN's performance was validated by comparing the baseline model with the trained models at two training levels. RESULTS: In prospective validation, the best model trained using continual learning achieved a sensitivity of 90.0%, specificity of 70.0%, and accuracy of 72.0%, with an average of 0.41 false positive clusters detected per MRI. For FCD segmentation, an average Dice coefficient of 0.56 was attained. The model's performance improved in each training phase while maintaining a high level of sensitivity. Continual learning outperformed classical learning in this regard. CONCLUSIONS: Our study presents a promising CNN for FCD detection and segmentation, exhibiting both high sensitivity and specificity. Furthermore, the model demonstrates continuous improvement with the inclusion of more clinical MRI data. We consider our CNN a valuable tool for automated, examiner-independent FCD detection in daily clinical practice, potentially addressing the underutilization of epilepsy surgery in drug-resistant focal epilepsy and thereby improving patient outcomes.
Asunto(s)
Imagen por Resonancia Magnética , Malformaciones del Desarrollo Cortical , Redes Neurales de la Computación , Humanos , Femenino , Malformaciones del Desarrollo Cortical/diagnóstico por imagen , Malformaciones del Desarrollo Cortical/cirugía , Imagen por Resonancia Magnética/métodos , Masculino , Adulto , Estudios Prospectivos , Adulto Joven , Epilepsia Refractaria/diagnóstico por imagen , Epilepsia Refractaria/cirugía , Procesamiento de Imagen Asistido por Computador/métodos , Adolescente , Algoritmos , Persona de Mediana Edad , Sensibilidad y Especificidad , Displasia Cortical FocalRESUMEN
Deep learning has been increasingly utilized in the medical field and achieved many goals. Since the size of data dominates the performance of deep learning, several medical institutions are conducting joint research to obtain as much data as possible. However, sharing data is usually prohibited owing to the risk of privacy invasion. Federated learning is a reasonable idea to train distributed multicenter data without direct access; however, a central server to merge and distribute models is needed, which is expensive and hardly approved due to various legal regulations. This paper proposes a continual learning framework for a multicenter study, which does not require a central server and can prevent catastrophic forgetting of previously trained knowledge. The proposed framework contains the continual learning method selection process, assuming that a single method is not omnipotent for all involved datasets in a real-world setting and that there could be a proper method to be selected for specific data. We utilized the fake data based on a generative adversarial network to evaluate methods prospectively, not ex post facto. We used four independent electrocardiogram datasets for a multicenter study and trained the arrhythmia detection model. Our proposed framework was evaluated against supervised and federated learning methods, as well as finetuning approaches that do not include any regulation to preserve previous knowledge. Even without a central server and access to the past data, our framework achieved stable performance (AUROC 0.897) across all involved datasets, achieving comparable performance to federated learning (AUROC 0.901).
Asunto(s)
Electrocardiografía , Estudios Multicéntricos como Asunto , Humanos , Conocimiento , PrivacidadRESUMEN
Domain continual medical image segmentation plays a crucial role in clinical settings. This approach enables segmentation models to continually learn from a sequential data stream across multiple domains. However, it faces the challenge of catastrophic forgetting. Existing methods based on knowledge distillation show potential to address this challenge via a three-stage process: distillation, transfer, and fusion. Yet, each stage presents its unique issues that, collectively, amplify the problem of catastrophic forgetting. To address these issues at each stage, we propose a tri-enhanced distillation framework. (1) Stochastic Knowledge Augmentation reduces redundancy in knowledge, thereby increasing both the diversity and volume of knowledge derived from the old network. (2) Adaptive Knowledge Transfer selectively captures critical information from the old knowledge, facilitating a more accurate knowledge transfer. (3) Global Uncertainty-Guided Fusion introduces a global uncertainty view of the dataset to fuse the old and new knowledge with reduced bias, promoting a more stable knowledge fusion. Our experimental results not only validate the feasibility of our approach, but also demonstrate its superior performance compared to state-of-the-art methods. We suggest that our innovative tri-enhanced distillation framework may establish a robust benchmark for domain continual medical image segmentation.
Asunto(s)
Benchmarking , Procesamiento de Imagen Asistido por Computador , Humanos , IncertidumbreRESUMEN
MOTIVATION: Cell-type annotation of single-cell RNA-sequencing (scRNA-seq) data is a hallmark of biomedical research and clinical application. Current annotation tools usually assume the simultaneous acquisition of well-annotated data, but without the ability to expand knowledge from new data. Yet, such tools are inconsistent with the continuous emergence of scRNA-seq data, calling for a continuous cell-type annotation model. In addition, by their powerful ability of information integration and model interpretability, transformer-based pre-trained language models have led to breakthroughs in single-cell biology research. Therefore, the systematic combining of continual learning and pre-trained language models for cell-type annotation tasks is inevitable. RESULTS: We herein propose a universal cell-type annotation tool, called CANAL, that continuously fine-tunes a pre-trained language model trained on a large amount of unlabeled scRNA-seq data, as new well-labeled data emerges. CANAL essentially alleviates the dilemma of catastrophic forgetting, both in terms of model inputs and outputs. For model inputs, we introduce an experience replay schema that repeatedly reviews previous vital examples in current training stages. This is achieved through a dynamic example bank with a fixed buffer size. The example bank is class-balanced and proficient in retaining cell-type-specific information, particularly facilitating the consolidation of patterns associated with rare cell types. For model outputs, we utilize representation knowledge distillation to regularize the divergence between previous and current models, resulting in the preservation of knowledge learned from past training stages. Moreover, our universal annotation framework considers the inclusion of new cell types throughout the fine-tuning and testing stages. We can continuously expand the cell-type annotation library by absorbing new cell types from newly arrived, well-annotated training datasets, as well as automatically identify novel cells in unlabeled datasets. Comprehensive experiments with data streams under various biological scenarios demonstrate the versatility and high model interpretability of CANAL. AVAILABILITY: An implementation of CANAL is available from https://github.com/aster-ww/CANAL-torch. CONTACT: dengmh@pku.edu.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Journal Name online.
Asunto(s)
Perfilación de la Expresión Génica , Programas Informáticos , Perfilación de la Expresión Génica/métodos , Análisis de Expresión Génica de una Sola Célula , Análisis de la Célula Individual/métodos , Lenguaje , Análisis de Secuencia de ARN/métodosRESUMEN
The ability to learn continuously is crucial for a robot to achieve a high level of intelligence and autonomy. In this paper, we consider continual reinforcement learning (RL) for quadruped robots, which includes the ability to continuously learn sub-sequential tasks (plasticity) and maintain performance on previous tasks (stability). The policy obtained by the proposed method enables robots to learn multiple tasks sequentially, while overcoming both catastrophic forgetting and loss of plasticity. At the same time, it achieves the above goals with as little modification to the original RL learning process as possible. The proposed method uses the Piggyback algorithm to select protected parameters for each task, and reinitializes the unused parameters to increase plasticity. Meanwhile, we encourage the policy network exploring by encouraging the entropy of the soft network of the policy network. Our experiments show that traditional continual learning algorithms cannot perform well on robot locomotion problems, and our algorithm is more stable and less disruptive to the RL training progress. Several robot locomotion experiments validate the effectiveness of our method.
RESUMEN
Deep-learning algorithms hold promise in processing physiological signal data, including electrocardiograms (ECGs) and electroencephalograms (EEGs). However, healthcare often requires long-term monitoring, posing a challenge to traditional deep-learning models. These models are generally trained once and then deployed, which limits their ability to adapt to the dynamic and evolving nature of healthcare scenarios. Continual learning-known for its adaptive learning capabilities over time-offers a promising solution to these challenges. However, there remains an absence of consolidated literature, which reviews the techniques, applications, and challenges of continual learning specific to physiological signal analysis, as well as its future directions. Bridging this gap, our review seeks to provide an overview of the prevailing techniques and their implications for smart healthcare. We delineate the evolution from traditional approaches to the paradigms of continual learning. We aim to offer insights into the challenges faced and outline potential paths forward. Our discussion emphasizes the need for benchmarks, adaptability, computational efficiency, and user-centric design in the development of future healthcare systems.
RESUMEN
This study introduces the Data Pyramid Structure (DPS) to address data sparsity and missing labels in medical image analysis. The DPS optimizes multi-task learning and enables sustainable expansion of multi-center data analysis. Specifically, It facilitates attribute prediction and malignant tumor diagnosis tasks by implementing a segmentation and aggregation strategy on data with absent attribute labels. To leverage multi-center data, we propose the Unified Ensemble Learning Framework (UELF) and the Unified Federated Learning Framework (UFLF), which incorporate strategies for data transfer and incremental learning in scenarios with missing labels. The proposed method was evaluated on a challenging EUS patient dataset from five centers, achieving promising diagnostic performance. The average accuracy was 0.984 with an AUC of 0.927 for multi-center analysis, surpassing state-of-the-art approaches. The interpretability of the predictions further highlights the potential clinical relevance of our method.
Asunto(s)
Análisis de Datos , Aprendizaje , Humanos , Procesamiento de Imagen Asistido por ComputadorRESUMEN
Humans and other animals navigate different environments effortlessly, their brains rapidly and accurately generalizing across contexts. Despite recent progress in deep learning, this flexibility remains a challenge for many artificial systems. Here, we show how a bio-inspired network motif can explicitly address this issue. We do this using a dataset of MNIST digits of varying transparency, set on one of two backgrounds of different statistics that define two contexts: a pixel-wise noise or a more naturalistic background from the CIFAR-10 dataset. After learning digit classification when both contexts are shown sequentially, we find that both shallow and deep networks have sharply decreased performance when returning to the first background - an instance of the catastrophic forgetting phenomenon known from continual learning. To overcome this, we propose the bottleneck-switching network or switching network for short. This is a bio-inspired architecture analogous to a well-studied network motif in the visual cortex, with additional "switching" units that are activated in the presence of a new background, assuming a priori a contextual signal to turn these units on or off. Intriguingly, only a few of these switching units are sufficient to enable the network to learn the new context without catastrophic forgetting through inhibition of redundant background features. Further, the bottleneck-switching network can generalize to novel contexts similar to contexts it has learned. Importantly, we find that - again as in the underlying biological network motif, recurrently connecting the switching units to network layers is advantageous for context generalization.
Asunto(s)
Encéfalo , Redes Neurales de la Computación , Humanos , Encéfalo/fisiología , Generalización PsicológicaRESUMEN
The classification problem is essential to machine learning, often used in fault detection, condition monitoring, and behavior recognition. In recent years, due to the rapid development of incremental learning, reinforcement learning, transfer learning, and continual learning algorithms, the contradiction between the classification model and new data has been alleviated. However, due to the lack of feedback, most classification algorithms take long to search and may deviate from the correct results. Because of this, we propose a continual learning classification method with human-in-the-loop (H-CLCM) based on the artificial immune system. H-CLCM draws lessons from the mechanism that humans can enhance immune response through various intervention technologies and brings humans into the test learning process in a supervisory role. The human experience is integrated into the test phase, and the parameters corresponding to the error identification data are adjusted online. It enables it to converge to an accurate prediction model at the lowest cost and to learn new data categories without retraining the classifier.â¢All necessary steps and formulas of H-CLCM are provided.â¢H-CLCM adds manual intervention to improve the classification ability of the model.â¢H-CLCM can recognize new types of data.