How deeply does The Art of AI Product Development cover catastrophic forgetting?

Defines the failure, identifies overlapping representations as a mechanism, and outlines evaluation and prevention decisions.

Catastrophic forgetting

As explained in The Art of AI Product Development

Catastrophic forgetting is the loss of previously learned knowledge when a model is trained on new tasks or data.

Catastrophic forgetting, also called catastrophic interference, occurs when fine-tuning causes a model to lose knowledge it previously acquired. Overlapping neural representations can overwrite older memories as the model learns new tasks. section 8.2.1

Detecting the trade-off

A model fine-tuned to resolve industry acronyms and summarize workflow concepts should also be tested on the benchmarks used before fine-tuning. A substantial decline on those earlier tasks signals catastrophic forgetting. section 8.2.1

Choose the response according to the task’s continuity and risk:

Use proactive prevention when continual learning requires the model to retain prior knowledge while adapting, especially in medical, legal, or compliance applications. section 8.2.1
Use a reactive approach for a highly specialized, independent task when prior knowledge matters less: monitor older-task performance before applying mitigation. section 8.2.1

How The Art of AI Product Development covers it

Cover of The Art of AI Product Development

liveBook manning.com

Read The Art of AI Product Development on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Reinforcement Learning from Human FeedbackCatastrophic forgetting is the rapid loss of previously learned capabilities or information when a model is trained on new objectives or data.
liveBook manning.com

Generative AI in ActionCatastrophic forgetting is the loss of previously learned knowledge or capabilities when a model is trained on new data or tasks.

Compare how 3 books explain catastrophic forgetting →

Related concepts

parameter-efficient fine-tuningaddressed by · Parameter-efficient fine-tuning adapts a pretrained model by training a limited subset of its parameters or added components rather than all its parameters.
low-rank adaptationaddressed by · Low-rank adaptation is a parameter-efficient fine-tuning method that adapts a model by learning low-rank updates to its weights, typically while keeping most original weights fixed.
Kullback–Leibler divergencemeasured by · Kullback–Leibler divergence is a nonnegative, directed measure of the information lost when one probability distribution approximates another, computed as an expected log ratio under the first distribution.
learning rateaddressed by · A learning rate is a step-size parameter that controls the magnitude of updates made by an iterative learning or optimization process.

This explainer was generated by Manning's knowledge graph from the text of The Art of AI Product Development. The section links point to the parts of the book it draws on.