📌 Catastrophic Forgetting Summary
Catastrophic forgetting is a problem in machine learning where a model trained on new data quickly loses its ability to recall or perform well on tasks it previously learned. This happens most often when a neural network is trained on one task, then retrained on a different task without access to the original data. As a result, the model forgets important information from earlier tasks, making it unreliable for multiple uses. Researchers are working on methods to help models retain old knowledge while learning new things.
🙋🏻♂️ Explain Catastrophic Forgetting Simply
Imagine trying to learn a new language, but every time you start a new one, you completely forget the last one you studied. Your brain cannot hold onto both at the same time. Catastrophic forgetting in machine learning is like this, where a computer forgets old skills when it learns something new.
📅 How Can it be used?
Apply techniques to prevent catastrophic forgetting when updating a chatbot with new conversation topics so it still remembers older ones.
🗺️ Real World Examples
A voice assistant trained to answer questions about home automation may forget how to answer questions about music controls if it is later updated with only home automation data. This makes the assistant less useful for users who expect it to handle both tasks.
An image recognition system in a factory is updated to detect new types of defects, but if catastrophic forgetting occurs, it may lose its ability to spot the defects it was originally designed to find, causing quality control issues.
✅ FAQ
📚 Categories
🔗 External Reference Links
Ready to Transform, and Optimise?
At EfficiencyAI, we don’t just understand technology — we understand how it impacts real business operations. Our consultants have delivered global transformation programmes, run strategic workshops, and helped organisations improve processes, automate workflows, and drive measurable results.
Whether you're exploring AI, automation, or data strategy, we bring the experience to guide you from challenge to solution.
Let’s talk about what’s next for your organisation.
💡Other Useful Knowledge Cards
Business Impact Assessment
A Business Impact Assessment is a process used by organisations to identify which functions and processes are most crucial to their operations. It helps determine the potential effects of disruptions, such as natural disasters or cyber-attacks, on key business areas. The assessment guides planning for how to reduce risks and recover quickly if something goes wrong.
Bayesian Hyperparameter Tuning
Bayesian hyperparameter tuning is a method for finding the best settings for machine learning models by using probability to guide the search. Instead of trying every combination or picking values at random, it learns from previous attempts and predicts which settings are likely to work best. This makes the search more efficient and can lead to better model performance with fewer trials.
Decentralized Identity Systems
Decentralised identity systems let people control their personal information without relying on a single organisation or central authority. Instead, users store and manage their identity details on their own devices or through secure, distributed networks. These systems use technologies like blockchain to help verify identity while keeping data private and secure.
Cloud and Infrastructure Transformation
Cloud and Infrastructure Transformation refers to the process organisations use to move their technology systems and data from traditional, on-site servers to cloud-based platforms. This shift often includes updating hardware, software, and processes to take advantage of cloud computing's flexibility and scalability. The goal is to improve efficiency, reduce costs, and support new ways of working, such as remote access and automation.
Data Workflow Automation
Data workflow automation is the process of using software to handle repetitive tasks involved in collecting, processing, and moving data. It reduces the need for manual work by automatically managing steps like data entry, transformation, and delivery. This helps organisations save time, reduce errors, and ensure data is handled consistently.