Episode 5: Entity Embeddings for Categorical Variables

Abhishek Thakur · Intermediate ·🔍 RAG & Vector Search ·6y ago
In this episode, I discuss what entity #embeddings for #categorical #variables are and how to implement them using tensorflow/keras. I have used the data from a Kaggle competition: https://www.kaggle.com/c/cat-in-the-dat-ii for this video. The task in this video is to convert the keras model to pytorch. You can find the full kernel here: https://www.kaggle.com/abhishek/same-old-entity-embeddings Follow me on: Twitter: https://twitter.com/abhi1thakur LinkedIn: https://www.linkedin.com/in/abhi1thakur/ Kaggle: https://kaggle.com/abhishek
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Abhishek Thakur · Abhishek Thakur · 13 of 60

1 Episode 1.1: Intro and building a machine learning framework
Episode 1.1: Intro and building a machine learning framework
Abhishek Thakur
2 Episode 1.2: Building an inference for the machine learning framework
Episode 1.2: Building an inference for the machine learning framework
Abhishek Thakur
3 Episode 2: A Cross Validation Framework
Episode 2: A Cross Validation Framework
Abhishek Thakur
4 Tips N Tricks #2: Setting up development environment for machine learning
Tips N Tricks #2: Setting up development environment for machine learning
Abhishek Thakur
5 Episode 3: Handling Categorical Features in Machine Learning Problems
Episode 3: Handling Categorical Features in Machine Learning Problems
Abhishek Thakur
6 BERT on Steroids: Fine-tuning BERT for a dataset using PyTorch and Google Cloud TPUs
BERT on Steroids: Fine-tuning BERT for a dataset using PyTorch and Google Cloud TPUs
Abhishek Thakur
7 Special Announcement: Approaching (almost) any machine learning problem
Special Announcement: Approaching (almost) any machine learning problem
Abhishek Thakur
8 Training BERT Language Model From Scratch On TPUs
Training BERT Language Model From Scratch On TPUs
Abhishek Thakur
9 Bengali.AI: Handwritten Grapheme Classification Using PyTorch (Part-1)
Bengali.AI: Handwritten Grapheme Classification Using PyTorch (Part-1)
Abhishek Thakur
10 Bengali.AI: Handwritten Grapheme Classification Using PyTorch (Part-2)
Bengali.AI: Handwritten Grapheme Classification Using PyTorch (Part-2)
Abhishek Thakur
11 Episode 4: Simple and Basic Binary Classification Metrics
Episode 4: Simple and Basic Binary Classification Metrics
Abhishek Thakur
12 Training Sentiment Model Using BERT and Serving it with Flask API
Training Sentiment Model Using BERT and Serving it with Flask API
Abhishek Thakur
Episode 5: Entity Embeddings for Categorical Variables
Episode 5: Entity Embeddings for Categorical Variables
Abhishek Thakur
14 Tips N Tricks #5: 3 Simple and Easy Ways to Cache Functions in Python
Tips N Tricks #5: 3 Simple and Easy Ways to Cache Functions in Python
Abhishek Thakur
15 Multi-Lingual Toxic Comment Classification using BERT and TPUs with PyTorch
Multi-Lingual Toxic Comment Classification using BERT and TPUs with PyTorch
Abhishek Thakur
16 Text Extraction From a Corpus Using BERT (AKA Question Answering)
Text Extraction From a Corpus Using BERT (AKA Question Answering)
Abhishek Thakur
17 10K Subscribers: Approaching (almost) Any Machine Learning Problem and Talk Show
10K Subscribers: Approaching (almost) Any Machine Learning Problem and Talk Show
Abhishek Thakur
18 Data Processing For Question & Answering Systems: BERT vs. RoBERTa
Data Processing For Question & Answering Systems: BERT vs. RoBERTa
Abhishek Thakur
19 Tips N Tricks #6: How to train multiple deep neural networks on TPUs simultaneously
Tips N Tricks #6: How to train multiple deep neural networks on TPUs simultaneously
Abhishek Thakur
20 Sentencepiece Tokenizer With Offsets For T5, ALBERT, XLM-RoBERTa And Many More
Sentencepiece Tokenizer With Offsets For T5, ALBERT, XLM-RoBERTa And Many More
Abhishek Thakur
21 Talks # 1:Andrey Lukyanenko - Handwritten digit recognition w/ a twist &  topic modelling over time
Talks # 1:Andrey Lukyanenko - Handwritten digit recognition w/ a twist & topic modelling over time
Abhishek Thakur
22 Episode 6: Simple and Basic Evaluation Metrics For Regression
Episode 6: Simple and Basic Evaluation Metrics For Regression
Abhishek Thakur
23 Talks # 2: Subhaditya Mukherjee - Image restoration using Deep Learning: Dehazing
Talks # 2: Subhaditya Mukherjee - Image restoration using Deep Learning: Dehazing
Abhishek Thakur
24 Basic git commands everyone should know about
Basic git commands everyone should know about
Abhishek Thakur
25 How do I start my career in Data Science?
How do I start my career in Data Science?
Abhishek Thakur
26 Talks # 3: Lorenzo Ampil - Introduction to T5 for Sentiment Span Extraction
Talks # 3: Lorenzo Ampil - Introduction to T5 for Sentiment Span Extraction
Abhishek Thakur
27 Detecting Skin Cancer (Melanoma) With Deep Learning
Detecting Skin Cancer (Melanoma) With Deep Learning
Abhishek Thakur
28 Talks # 4: Sebastien Fischman - Pytorch-TabNet: Beating XGBoost on Tabular Data Using Deep Learning
Talks # 4: Sebastien Fischman - Pytorch-TabNet: Beating XGBoost on Tabular Data Using Deep Learning
Abhishek Thakur
29 Build a web-app to serve a deep learning model for skin cancer detection
Build a web-app to serve a deep learning model for skin cancer detection
Abhishek Thakur
30 Talks # 5: Parul Pandey: Data Science, Diversity and Kaggle
Talks # 5: Parul Pandey: Data Science, Diversity and Kaggle
Abhishek Thakur
31 Implementing original U-Net from scratch using PyTorch
Implementing original U-Net from scratch using PyTorch
Abhishek Thakur
32 Tips N Tricks # 8: Using automatic mixed precision training with PyTorch 1.6
Tips N Tricks # 8: Using automatic mixed precision training with PyTorch 1.6
Abhishek Thakur
33 Talks # 6: Mani Sarkar: From backend development to machine learning
Talks # 6: Mani Sarkar: From backend development to machine learning
Abhishek Thakur
34 Dockerizing the skin cancer detection web application
Dockerizing the skin cancer detection web application
Abhishek Thakur
35 How to train a deep learning model using docker?
How to train a deep learning model using docker?
Abhishek Thakur
36 Building an entity extraction model using BERT
Building an entity extraction model using BERT
Abhishek Thakur
37 Train custom object detection model with YOLO V5
Train custom object detection model with YOLO V5
Abhishek Thakur
38 Talks # 7: Moez Ali: Machine learning with PyCaret
Talks # 7: Moez Ali: Machine learning with PyCaret
Abhishek Thakur
39 How to convert almost any PyTorch model to ONNX and serve it using flask
How to convert almost any PyTorch model to ONNX and serve it using flask
Abhishek Thakur
40 Hyperparameter Optimization: This Tutorial Is All You Need
Hyperparameter Optimization: This Tutorial Is All You Need
Abhishek Thakur
41 I finally got a copy of "Approaching (Almost) Any Machine Learning Problem"
I finally got a copy of "Approaching (Almost) Any Machine Learning Problem"
Abhishek Thakur
42 Captcha recognition using PyTorch (Convolutional-RNN + CTC Loss)
Captcha recognition using PyTorch (Convolutional-RNN + CTC Loss)
Abhishek Thakur
43 Live Q&A: Getting Started With Data Science
Live Q&A: Getting Started With Data Science
Abhishek Thakur
44 WTFML: Simple, reusable code for PyTorch models
WTFML: Simple, reusable code for PyTorch models
Abhishek Thakur
45 Talks # 8: Sebastián Ramírez; Build a machine learning API  from scratch  with FastAPI
Talks # 8: Sebastián Ramírez; Build a machine learning API from scratch with FastAPI
Abhishek Thakur
46 Data Science PC Configs: From Low Range to Super-High Range
Data Science PC Configs: From Low Range to Super-High Range
Abhishek Thakur
47 BERT Model Architectures For Semantic Similarity
BERT Model Architectures For Semantic Similarity
Abhishek Thakur
48 I just got access to GitHub's Codespaces and it's amazing!
I just got access to GitHub's Codespaces and it's amazing!
Abhishek Thakur
49 Talks # 9: Vladimir Iglovikov; Detecting Masked Faces In The Pandemic World
Talks # 9: Vladimir Iglovikov; Detecting Masked Faces In The Pandemic World
Abhishek Thakur
50 Tips To Build A Good Data Science / Machine Learning Project (For Your Portfolio)
Tips To Build A Good Data Science / Machine Learning Project (For Your Portfolio)
Abhishek Thakur
51 Docker For Data Scientists
Docker For Data Scientists
Abhishek Thakur
52 How To Become A Data Scientist In 1 Year (Learn From A Real World Example)
How To Become A Data Scientist In 1 Year (Learn From A Real World Example)
Abhishek Thakur
53 Talks # 10: Tanishq Abraham; What are CycleGANs? (a novel deep learning tool in pathology)
Talks # 10: Tanishq Abraham; What are CycleGANs? (a novel deep learning tool in pathology)
Abhishek Thakur
54 Deploy Any Machine Learning Or Deep Learning Model On Google Cloud Platform (App Engine)
Deploy Any Machine Learning Or Deep Learning Model On Google Cloud Platform (App Engine)
Abhishek Thakur
55 Pair Programming: Deep Learning Model For Drug Classification With Andrey Lukyanenko
Pair Programming: Deep Learning Model For Drug Classification With Andrey Lukyanenko
Abhishek Thakur
56 VS Code (codeserver) on Google Colab / Kaggle / Anywhere
VS Code (codeserver) on Google Colab / Kaggle / Anywhere
Abhishek Thakur
57 Talks # 11: Jean-François Puget; Did you know GPUs are not just for Deep Learning?
Talks # 11: Jean-François Puget; Did you know GPUs are not just for Deep Learning?
Abhishek Thakur
58 End-to-End: Automated Hyperparameter Tuning For Deep Neural Networks
End-to-End: Automated Hyperparameter Tuning For Deep Neural Networks
Abhishek Thakur
59 Deploy Any Machine Learning (or Deep Learning) Endpoint on Google Cloud Platform In 10 minutes
Deploy Any Machine Learning (or Deep Learning) Endpoint on Google Cloud Platform In 10 minutes
Abhishek Thakur
60 Ensembling, Blending & Stacking
Ensembling, Blending & Stacking
Abhishek Thakur

Related AI Lessons

Most Companies Doing GenAI Are Really Just Doing RAG: RAGOps Explained for analysts
Learn why RAGOps is becoming the preferred approach for GenAI projects and how it differs from agent-based approaches
Medium · RAG
RAG - Sliding Window, Token Based Chunking and PDF Chunking Packages
Learn about RAG chunking mechanisms, including Sliding Window, Token Based, and PDF Chunking, to improve your AI model's text processing capabilities
Dev.to AI
Ever Wondered How to Make Your RAG More Effective?
Improve your RAG effectiveness by connecting instead of searching
Medium · RAG
Why StarRocks Is Better Than Elasticsearch for RAG and AI-Powered Vector Search Analytics
Learn why StarRocks outperforms Elasticsearch for RAG and AI-powered vector search analytics, and how to apply this knowledge to improve your data architecture
Medium · LLM
Up next
Watch this before applying for jobs as a developer.
Tech With Tim
Watch →