Live briefing
Everything about Catastrophic interference
AI's tendency to abruptly and drastically forget old info after learning new info
Catastrophic interference, also known as catastrophic forgetting, is the tendency of an artificial neural network to abruptly and drastically forget previously learned information upon learning new information. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Catastrophic interferenceA 5-minute orientation
- Skim a recent paper: A neuro-inspired computational model of life-long learning and catastrophic interference, mimicking hippocampus novelty-based dopamine modulation and lateral inhibitory plasticityInfluential work since 2022
- Pick up a classic book: Treaty Occupationay ToxicologyThe most-reprinted book on the subject
- Read the landmark paper: When somatic information threatens, catastrophic thinking enhances attentional interferenceCited 279 times
- Go sideways: Types of artificial neural networksA closely related topic
- Go sideways: BackpropagationA closely related topic
📖 Definitions
Noun The tendency of an artificial neural network to forget previously learned information completely and abruptly upon learning new information.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
When somatic information threatens, catastrophic thinking enhances attentional interference
A functional hypothesis for adult hippocampal neurogenesis: Avoidance of catastrophic interference in the dentate gyrus
Life-long learning Cell Structures—continuously learning without catastrophic interference
Neocortical catastrophic interference in healthy and amnesic adults: A paradoxical matter of time
Critical periods and catastrophic interference effects in the development of self‐organizing feature maps
Defining pain and interference recovery trajectories after acute non-catastrophic musculoskeletal trauma through growth mixture modeling
Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation
Task Incremental Learning With Static Memory for Audio Classification Without Catastrophic Interference
🆕 Influential since 2022
A neuro-inspired computational model of life-long learning and catastrophic interference, mimicking hippocampus novelty-based dopamine modulation and lateral inhibitory plasticity
Why Lifelong Learning Fails for Materials Property Prediction: Catastrophic Interference in Sequential Fine-Tuning
Human Interference with the Earth Has Abolished the Next Ice Age but Overdosing with Carbon Dioxide Emissions Could Have Catastrophic Consequences
📚 Books worth reading
Treaty Occupationay ToxicologySuelen Queiroz · 2010
The Conspirators HierarchyJohn Coleman · 1992
Handbook of Corrosion EngineeringPierre R. Roberge · 1999
The Psychology of Learning and Motivation, 24Gordon H. Bower · 1989- 📕Nutrition in intensive care medicinePierre Singer · 2013
ROHAN IDEA OF POLUTION.ROHAN CHOUDHARY. · 2009
THE ENEMY INSIDE · 2013
DIMENSIONS OF PRAYER · 2018
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Types of artificial neural networks Types of neural networks (NN) include a family of techniques. The simplest types have static components, including number of units, number of layers, unit…
- Backpropagation In machine learning, backpropagation is a gradient computation method commonly used for training a neural network in computing parameter updates. It is…
- Holographic associative memory For holographic data storage, holographic associative memory (HAM) is an information storage and retrieval system based on the principles of holography…
- Recurrent neural network In artificial neural networks, recurrent neural networks (RNNs) are designed for processing sequential data, such as text, speech, and time series, where…
- Feedforward neural network A feedforward neural network is an artificial neural network in which information flows in a single direction – inputs are multiplied by weights to obtain…
- Echo state network An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer (with typically…
- Long short-term memory Long short-term memory (LSTM) is a type of recurrent neural network (RNN) aimed at mitigating the vanishing gradient problem commonly encountered by traditional…
- Connectionism Connectionism is an approach to the study of human mental processes and cognition that utilizes mathematical models known as connectionist networks or…