25 papers · ranked by Valyu relevance
Yong Luo, Liancheng Yin, Wenchao Bai, Keming Mao
As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is expected to have the ability of memorization and it is regarded as one of the ultimate goals of artificial intelligence technology. However…
Syed Shakib Sarwar, Aayush Ankit, Kaushik Roy
Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high computational time and energy requirements. Also, previously seen training samples may…
Jie Li, Junpei Zhong, Jingfeng Yang, Chenguang Yang
Though a robot can reproduce the demonstration trajectory from a human demonstrator by teleoperation, there is a certain error between the reproduced trajectory and the desired trajectory. To minimize this error, we propose a multimodal incremental learning framework based on a teleoperation strategy that can enable…
German I. Parisi, Jun Tani, Cornelius Weber, Stefan Wermter
Artificial autonomous agents and robots interacting in complex environments are required to continually acquire and fine-tune knowledge over sustained periods of time. The ability to learn from continuous streams of information is referred to as lifelong learning and represents a long-standing challenge for neural…
Takazumi Matsumoto, Wataru Ohata, Jun Tani, Maxwell Ramstead + 5 more
'Axel Constant' 'Thomas Parr' 'Anjali Bhat' 'Giovanni Pezzulo' 'Rosalyn Moran'] This study investigated how a physical robot can adapt goal-directed actions in dynamically changing environments, in real-time, using an active inference-based approach with incremental learning from human tutoring examples. Using our…
Jonghong Kim, WonHee Lee, Sungdae Baek, Jeong-Ho Hong + 2 more
'Marina Gavrilova'] Catastrophic forgetting, which means a rapid forgetting of learned representations while learning new data/samples, is one of the main problems of deep neural networks. In this paper, we propose a novel incremental learning framework that can address the forgetting problem by learning new incoming…
Mingxiao Ma, Shunyao Zhu, Guoliang Kang
Incremental object detection (IOD) aims to continuously expand the capability of a model to detect novel categories while preserving its performance on previously learned ones. When adopting a transformer-based detection model (e.g., DETR) to perform IOD, catastrophic knowledge forgetting may inevitably occur, which…
Vali Ollah Maraghi, Karim Faez
Recognition of activities in the video is an important field in computer vision. Many successful works have been done on activity recognition and they achieved acceptable results in recent years. However, their training is completely static, meaning that all classes are taught to the system in one training step. The…
Yu Li, Zhongxiao Li, Lizhong Ding, Yuhui Hu + 2 more
In most biological data sets, the amount of data is regularly growing and the number of classes is continuously increasing. To deal with the new data from the new classes, one approach is to train a classification model, e.g., a deep learning model, from scratch based on both old and new data. This approach is highly…
Ragav Venkatesan, Hemanth Venkateswara, Sethuraman Panchanathan, Baoxin Li
'Baoxin Li'] Multi-class supervised learning systems require the knowledge of the entire range of labels they predict. Often when learnt incrementally, they suffer from catastrophic forgetting. To avoid this, generous leeways have to be made to the philosophy of incremental learning that either forces a part of the…
Mert Kilickaya, Joost van de Weijer, Yuki M. Asano
The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However, for many applications, non-incremental learning is unrealistic. To that end…
Jiangpeng He, Runyu Mao, Zeman Shao, Fengqing Zhu
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life applications: (1) Learning new classes makes the trained model quickly forget old…
Mohammad Rostami, Aram Galstyan
Humans continually expand their learned knowledge to new domains and learn new concepts without any interference with past learned experiences. In contrast, machine learning models perform poorly in a continual learning setting, where input data distribution changes over time. Inspired by the nervous system learning…
Eden Belouadah, Adrian Popescu, Umang Aggarwal, Léo Saci
Incremental Learning (IL) allows AI systems to adapt to streamed data. Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1) new data are assumed to be readily annotated when streamed and (2) tests are run with balanced datasets while most real-life datasets are…
Muhammad Burhan Hafez, Kerim Erekmen
Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each task requires significant training time. Addressing the problem of continual learning necessitates various methods due to the complexity of…
Jihyea Lee, Jerald D. Kralik, YuJin Cha, Jee Hang Lee + 1 more
Causal reasoning is a principal higher-cognitive ability of humans, however, much remains unknown, including (a) the type (systematic versus intermixed) and order (inductive-then-deductive or vice versa) of experience that best achieves causal-chain extraction; (b) how inferences generalize to novel problems…
Leila Montaser-Kouhsari, Jonathan Nicholas, Raphael T. Gerraty, Daphna Shohamy
Patients with Parkinson’s disease are impaired at incremental reward-based learning. It is typically assumed that this impairment reflects a loss of striatal dopamine. However, many open questions remain about the nature of reward-based learning deficits in Parkinson’s. Recent studies have found that a combination of…
William L. Tong, Anisha Iyer, Venkatesh N. Murthy, Gautam Reddy
Dogs and laboratory mice are commonly trained to perform complex tasks by guiding them through a curriculum of simpler tasks (‘shaping’). What are the principles behind effective shaping strategies? Here, we propose a machine learning framework for shaping animal behavior, where an autonomous teacher agent decides its…
F. Bouchacourt, S. Tafazoli, M.G. Mattar, T.J. Buschman + 1 more
When performing a task in a changing world, sometimes we switch between rules already learned; at other times we must learn rules anew. Often we must do both, switching between known rules while also constantly re-estimating them. Here, we show these two processes, rule switching and rule learning, rely on distinct but…
Jonathan Nicholas, Marcelo G. Mattar
Our experiences contain countless details that may be important in the future, yet we rarely know which will matter and which won’t. This uncertainty poses a difficult challenge for adaptive decision making, as failing to preserve relevant information can prevent us from making good choices later on. One solution to…
Authors not listed
Large Language Models (LLMs) based on transformer architectures excel at internet-scale tasks. However, real-world scientific scenarios—such as synthetic chemistry laboratories and autonomous experimental setups—typically involve incremental data generation in batches as new chemical reactions are conducted, unlike…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Yannick Ureel, Maarten R. Dobbelaere, Yi Ouyang, Kevin De Ras + 3 more
By combining machine learning with design of experiments, so-called active machine learning, more efficient and cheaper research can be conducted. Machine learning algorithms are more flexible, and are better at investigating the processes spanning all length scales of chemical engineering. While the active machine…
Simon Viet Johansson, Hampus Gummesson Svensson, Esben Bjerrum, Alexander Schliep + 3 more
Computer aided synthesis planning is a rapidly growing field for suggesting synthetic routes for molecules of interest. The methods used are usually dependent on access to large datasets for training, but with a finite experimental budget there are limitations on how much data can be obtained from experiments. Active…
Muhammad Hanzla, Abdul Rehman Shinwari
Machine Learning (ML) can be defined as a class of Artificial Intelligence for automated data analysis, which is capable of detecting patterns in data. The extracted patterns can be used to predict un-known data or to assist in decision-making processes under uncertainty. Recent advances in experimental and…