🕸️
Deep Learning
  • 💫Deep Learning Notes
  • 💼Practical Tools
  • 💎Concepts of Neural Networks
    • 🌱Introduction
    • 🔎The Problem in General
    • 👷‍♀️ Implementation Notes
    • 📚Common Concepts
    • 💥Activation Functions
    • 🎈Practical Aspects
    • 👩‍🔧 NN Regularization
    • ✨Optimization Algorithms
    • 🎨Softmax Regression
    • 🏃‍♀️ Introduction to Tensorflow
    • 👩‍💻 Python Code Snippets
  • 🙋‍♀️ Hello World of Deep Learning with Neural Networks
    • 🌱Introduction
    • 🌐CNNs In Browser
  • 🚪Introduction to Computer Vision
    • 🌱Introduction
  • 🚩Concepts of Convolutional Neural Networks
    • 🌱Introduction
    • 📌Common Concepts
    • 🌟Advanced Concepts
    • 👀Visualization
    • 👵Classic Networks
    • ✨Other Approaches
    • 🕸️Common Applications
  • 👩‍💻 Works and Notes on CNNs
    • 🌱Introduction
  • 💄Popular Strategies of Deep Learning
    • 🌱Introduction
    • 🚙Transfer Learning
    • 📚Other Strategies
  • 🤡Image Augmentation
    • 🌱Introduction
  • 🤸‍♀️ Notes on Applied Machine Learning
    • 🌱Introduction
    • 👩‍🔧 Notes on Structuring Machine Learning Projects
    • 👩‍🏫 Implementation Guidelines
  • 🕵️‍♀️ Basics of Object Detection
    • 🌱Introduction
    • ⭕Region-Based CNNs
    • 🤳SSD and YOLO
    • 🤖TensorFlow Object Detection API
    • 🐞Model Debugging
  • ➰Sequence Models In Deep Learning
    • 🌱Introduction
    • 📚General Concepts
    • 🔄Recurrent Neural Networks
    • 🌌Vanishing Gradients with RNNs
    • 🌚Word Representation
    • 💬Mixed Info On NLP
  • 💬NLP
    • 🌱Introduction
  • 💬Applied NLP
    • 🙌🏻 Handling texts
    • 🧩Regex
  • 👀Quick Visual Info
  • 📚PDFs that I found and recommend
Powered by GitBook
On this page
  • ✨ How to effectively set up evaluation metrics?
  • 📚 Types of Metrics
  • 🚀 How to set up datasets to maximize the efficiency
  • 👩‍🏫 Guideline
  • 🤔 How to choose the size of sets
  • 🙄 When to change dev/test sets and metrics

Was this helpful?

Export as PDF
  1. 🤸‍♀️ Notes on Applied Machine Learning

👩‍🔧 Notes on Structuring Machine Learning Projects

Make your training procedure more effective

PreviousIntroductionNext👩‍🏫 Implementation Guidelines

Last updated 4 years ago

Was this helpful?

✨ How to effectively set up evaluation metrics?

  • While looking to precesion P and recall R (for example) we may be not able to choose the best model correctly

    • So we have to create a new evaluation metric that makes a relation between P and R

    • Now we can choose the best model due to our new metric 🐣

    • For example: (as a popular associated metric) F1 Score is:

      • F1=21P+1RF1 = \frac{2}{\frac{1}{P}+\frac{1}{R}}F1=P1​+R1​2​

To summarize: we can construct our own metrics due to our models and values to be able to get the best choice 👩‍🏫

📚 Types of Metrics

For better evaluation we have to classify our metrics as the following:

Metric Type

Description

✨ Optimizing Metric

A metric that has to be in its best value

🤗 Satisficing Metric

A metric that just has to be good enough

Technically, If we have N metrics we have to try to optimize 1 metric and to satisfice N-1 metrics 🙄

🙌 Clarification: we tune satisficing metrics due to a threshold that we determine

🚀 How to set up datasets to maximize the efficiency

  • It is recommended to choose the dev and test sets from the same distribution, so we have to shuffle the data randomly and then split it.

  • As a result, both test and dev sets have data from all categories ✨

👩‍🏫 Guideline

We have to choose a dev set and test set - from same distribution - to reflect data we expect to get in te future and consider important to do well on

🤔 How to choose the size of sets

  • If we have a small dataset (m < 10,000)

    • 60% training, 20% dev, 20% test will be good

  • If we have a huge dataset (1M for example)

    • 99% trainig, %1 dev, 1% test will be acceptable

      And so on, considering these two statuses we can choose the correct ratio 👮‍

🙄 When to change dev/test sets and metrics

Guideline: if doing well on metric + dev/test set and doesn't correspond to doing well in the real world application, we have to change our metric and/or dev/test set 🏳