Finding online neural update rules by learning to remember
We investigate learning of the online local update rules for neural activations (bodies) and weights (synapses) from scratch. We represent the states of each weight and activation by small vectors, and parameterize their updates using (meta-) neural networks. Different neuron types are represented by different embedding vectors which allows the same two functions to be used for all neurons. Instead of training directly for the objective using evolution or long term back-propagation, as is commonly done in similar systems, we motivate and study a different objective: That of remembering past snippets of experience. We explain how this objective relates to standard back-propagation training and other forms of learning. We train for this objective using short term back-propagation and analyze the performance as a function of both the different network types and the difficulty of the problem. We find that this analysis gives interesting insights onto what constitutes a learning rule. We also discuss how such system could form a natural substrate for addressing topics such as episodic memories, meta-learning and auxiliary objectives.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningSimilar Papers 제목 키워드 기반
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
We give a model of how to infer natural language rules by doing experiments. The model integrates Large Language Models (LLMs) with Monte Carlo algorithms for probabilistic inference, interleaving online belief updates w…
One system for learning and remembering episodes and rules
Humans can learn individual episodes and generalizable rules and also successfully retain both kinds of acquired knowledge over time. In the cognitive science literature, (1) learning individual episodes and rules and (2…
Cost Trade-offs in Matrix Inversion Updates for Streaming Outlier Detection
Outlier detection identifies data points that deviate significantly from expected patterns, revealing anomalies that may require special attention. Incorporating online learning further improves accuracy by continuously …
Outlier DetectionBAM: Bayes with Adaptive Memory
Online learning via Bayes' theorem allows new data to be continuously integrated into an agent's current beliefs. However, a naive application of Bayesian methods in non stationary environments leads to slow adaptation a…
BAM: Bayes Augmented with Memory
Online learning via Bayes' theorem allows new data to be continuously integrated into an agent's current beliefs. However, a naive application of Bayesian methods in non-stationary environments leads to slow adaptation a…