NLP Demystified 7: Building Models (ML modelling overview, bias, variance, evaluation)

preview_player
Показать описание

Through a high-level overview of modelling, we'll
- clearly define "machine learning"
- look at the different types of machine learning
- learn how to evaluate model performance
- learn what bias and variance are
- see what to do about overfitting and underfitting
- explore practical concerns for model deployment.

If you're familiar with the process of building ML models, you can skip this module.

No colab notebook for this module.

Timestamps:
00:00:00 Building models
00:01:03 Scenarios for using machine learning
00:01:42 Defining machine learning
00:02:05 The different types of machine learning
00:04:20 Machine learning as automatic programming
00:05:59 A high-level view of modelling workflow
00:09:17 High bias and what to do about it
00:10:25 High variance and what to do about it
00:12:08 Regularization and hyperparameters
00:13:09 Evaluating on the test set
00:14:00 Practical concerns beyond performance metric
00:15:25 Modelling recap

This video is part of Natural Language Processing Demystified --a free, accessible course on NLP.

  1. Future Mojo
  2. natural language processing
  3. nlp
  4. bias
  5. variance
  6. overfitting
Рекомендации по теме
NLP Demystified 7: 0:16:14

NLP Demystified 7: Building Models (ML modelling overview, bias, variance, evaluation)

NLP Demystified 5: 0:20:12

NLP Demystified 5: Basic Bag-of-Words and Measuring Document Similarity

NLP Demystified 1: 0:08:48

NLP Demystified 1: Introduction

NLP Demystified 9: 0:47:05

NLP Demystified 9: Automatically Finding Topics in Documents with Latent Dirichlet Allocation

NLP Demystified 11: 0:58:56

NLP Demystified 11: Essential Training Techniques for Neural Networks

NLP Demystified 6: 0:12:26

NLP Demystified 6: TF-IDF and Simple Document Search

Natural Language Processing 0:05:29

Natural Language Processing In 5 Minutes | What Is NLP And How Does It Work? | Simplilearn

NLP Demystified 13: 0:59:25

NLP Demystified 13: Recurrent Neural Networks and Language Models

NLP Modeling Demystified: 0:08:57

NLP Modeling Demystified: Common Mistakes to Avoid & Skills to Acquire

How Large Language 0:05:34

How Large Language Models Work

NLP Demystified 12: 0:42:47

NLP Demystified 12: Capturing Word Meaning with Embeddings

NLP Demystified 2: 0:08:15

NLP Demystified 2: Text Tokenization

NLP Demystified 10: 1:10:05

NLP Demystified 10: Neural Networks From Scratch

Transformer models and 0:11:38

Transformer models and BERT model: Overview

How to build 0:00:53

How to build an NLP model in a few clicks with ML.NET

Attention is all 0:58:04

Attention is all you need (Transformer) - Model explanation (including math), Inference and Training

LLM Explained | 0:04:17

LLM Explained | What is LLM

NLP Demystified 4: 0:22:21

NLP Demystified 4: Advanced Preprocessing (part-of-speech tagging, entity tagging, parsing)

NLP Demystified 14: 1:06:56

NLP Demystified 14: Machine Translation With Sequence-to-Sequence and Attention

AI Demystified: Word 0:00:56

AI Demystified: Word Embeddings

What are Generative 0:08:47

What are Generative AI models?

But what is 0:18:40

But what is a neural network? | Chapter 1, Deep learning

NLP Demystified 8: 0:38:19

NLP Demystified 8: Text Classification With Naive Bayes (+ precision and recall)

The Complete Machine 0:05:25

The Complete Machine Learning Roadmap [2024]

Комментарии
Автор

I've watched a couple of videos and I am truly stunned. How on earth is it possible for this series to have only ...a couple of dozen views?! This is hands down the best intro course I've ever encountered. You've done an outstanding job sir - and even that's an understatement! :)

blendercomp
Автор

I'm a research Scholar and came across your channel. I was truly amazed at how you broke through the concepts and explained them.

LakshmiDevilifentravels
Автор

Amazing content. I appreciate the effort you have put into making this series and will recommend it everywhere possible. Let's get this channel a significant number of views. Totally deserved. Keep up the excellent work.

ddljgex
Автор

Best explanation. Crisp and exhaustive.

SawanSalhotra
Автор

Timestamps:
00:00:00 Building models
00:01:03 Scenarios for using machine learning
00:01:42 Defining machine learning
00:02:05 The different types of machine learning
00:04:20 Machine learning as automatic programming
00:05:59 A high-level view of modelling workflow
00:09:17 High bias and what to do about it
00:10:25 High variance and what to do about it
00:12:08 Regularization and hyperparameters
00:13:09 Evaluating on the test set
00:14:00 Practical concerns beyond performance metric
00:15:25 Modelling recap

futuremojo
Автор

For a deeper clarification, when does a model become become a model?

amparoconsuelo
Автор

It would be great if u can help us in giving the ppt of the context that u present in the videos, the best way to source it out will be embedding it in your website. Love ur content❤

bismaybibhuprakash
Автор

You definitely need to change the name of the channel, "t15" is not memorable and you'll get fewer clicks than you deserve for awesome material like this.

DmytroKulaiev