Understand the limitations of your dataset and model - Deepstash

Understand the limitations of your dataset and model

  • A model trained to detect correlations should not be used to make causal inferences, or imply that it can.Β 
  • Machine learning models today are largely a reflection of the patterns of their training data.
  • Communicate limitations to users where possible.

35

298 reads

CURATED FROM

IDEAS CURATED BY

anikad

Life Is A Marathon| Life Lover

The idea is part of this collection:

Machine Learning With Google

Learn more about philosophy with this collection

Understanding machine learning models

Improving data analysis and decision-making

How Google uses logic in machine learning

Related collections

Similar ideas to Understand the limitations of your dataset and model

Transfer learning concept

The biggest problem, thoug h, is that models like this one are performed only on a single task. Future tasks require a new set of data points as well as equal or more amount of resources.

Transfer learning is an approach in deep learning (and machine learning) where knowledge is ...

Read & Learn

20x Faster

without
deepstash

with
deepstash

with

deepstash

Personalized microlearning

β€”

100+ Learning Journeys

β€”

Access to 200,000+ ideas

β€”

Access to the mobile app

β€”

Unlimited idea saving

β€”

β€”

Unlimited history

β€”

β€”

Unlimited listening to ideas

β€”

β€”

Downloading & offline access

β€”

β€”

Supercharge your mind with one idea per day

Enter your email and spend 1 minute every day to learn something new.

Email

I agree to receive email updates