Tutorial - Continual Learning beyond classification

Abstract

Continual Learning (CL, sometimes also termed incremental learning) is a flavor of machine learning where the usual assumption of stationary data distribution is relaxed or omitted. When naively applying, e.g., DNNs in CL problems, changes in the data distribution can cause the so-called catastrophic forgetting (CF) effect: an abrupt loss of previous knowledge. Although many significant contributions to enabling CL have been made in recent years, most works address supervised (classification) problems. This article reviews literature that study CL in other settings, such as learning with reduced supervision, fully unsupervised learning, and reinforcement learning. Besides proposing a simple schema for classifying CL approaches w.r.t. their level of autonomy and supervision, we discuss the specific challenges associated with each setting and the potential contributions to the field of CL in general. Framework and Goals of Continual LearningContinual learning (CL) is a machine learning sub-field that studies learning under time-varying data distributions. This relaxes one of the fundamental assumptions of statistical learning theory ([1]), which states that the data follows 67

Development and Assessment of Machine Learning Models for Individualized Risk Assessment of Mastectomy Skin Flap Necrosis

“…Furthermore, unlike conventional statistical methods that are static, ML can improve over time when new data are provided, a process known as incremental learning. 39,40 These findings demonstrate that artificial intelligence models outperform conventional statistical methods in predicting MSFN and encourage the use of ML to provide individualized risk assessment.…”

Few-Shot Object Detection: A Comprehensive Survey

“…3) Incremental Learning: Typical deep-learning approaches suffer from catastrophic forgetting when the model is trained on new data. In contrast, incremental learning approaches [20], [21], [22] aim to retain the performance on old categories when new categories are added incrementally. Some FSOD approaches also incorporate incremental learning techniques.…”

Incremental Learning with Neural Network Algorithm for the Monitoring Pre-Convective Environments Using Geostationary Imager

“…'Concept drift', a term used in the field of machine learning, means that the statistical characteristics of a target variable change over time [45,46]. If the concept drift occurs in the ST ANN, re-training using the entire learning data may not reflect the concept drift.…”

“…Figure 5 shows an example of the process of updating from t − 1 to t. To find the proper length of the window is challenging. For example, a short length of the sliding window can lead to a big difference and high variance in the next sequence whereas a long one leads to heavy computational load and decreased reactivity of the system [46,51]. To determine an optimal window size in between the two extremes, an empirical experiment that tests error statistics depending on the update cycle from the 1st to the 14th with a one-day interval has been conducted [51,52].…”