Overview

Incremental learning studies how a model can learn from data that arrives over time—such as new classes, changing domains, or streaming examples—without losing what it learned before. Common approaches replay stored examples, regularize or distill the model to preserve earlier behavior, or isolate and expand parts of the model with adapters, experts, or new parameters. Methods are evaluated in settings such as class-, domain-, and task-incremental learning, using benchmarks including CIFAR-100, ImageNet variants, and language-task sequences; newer work also considers pretrained multimodal models, long-tailed data, and task-free streams. The central tension is stability versus plasticity: preserving old knowledge can hinder learning new information, while memory, model growth, task-order effects, and realistic evaluation remain open challenges.

Latest papers

151 papers7 papers in the last four weeks, down 70% on the four weeks before. 0.1% of all new papers.

Jul 31, 2022

Interpretable Machine Learning: Can the EnglishLike Programming Language be the Future of ChatIPC and ChatIPCv2?

The development of interpretable machine learning requires more than the ability to produce predictions accompanied by explanations. It requires computational systems whose internal representations, decision procedures, constraints, and execution paths can be inspected, reproduced, and modified by humans. This paper investigates whether EnglishLike, an English-like, object-oriented programming language implemented in C++17, could provide the symbolic programming and execution foundation for the ChatIPC and its subsequent implementation, ChatIPCv2. The investigation is based on a comparative examination of the publicly available ChatIPC.cpp and ChatIPCv2.cpp implementations in the PCNTechnologyEnterprise Hugging Face repository, together with the EnglishLike 2.2 implementation available in the associated project materials. ChatIPC combines incrementally learned token-transition relationships with dictionary derived semantic information, part-of-speech information, Jaccard similarity, grammatical heuristics, repetition penalties, and deterministic candidate selection. ChatIPCv2 introduces a different generation strategy based on token identifiers, historical-context bitsets, multi-depth graph exploration, n-gram backoff, and parallel candidate evaluation. EnglishLike provides a complementary computational abstraction: a structured language for expressing declarations, functions, classes, interfaces, control flow, and executable rules. Its compiler, bytecode verifier, and virtual machine provide a potentially useful foundation for representing and executing symbolic reasoning procedures.