|
About the Deep Learning category
|
|
36
|
8999
|
May 30, 2026
|
|
This week, I rebuilt my movie recommender from scratch and adapted it to predict restaurant ratings. Using only diner and restaurant IDs, my model had 29% lower validation mean squared error than predicting the training set’s average rating for everyone
|
|
4
|
46
|
November 9, 2026
|
|
Single place for my blog posts
|
|
1
|
22
|
November 6, 2026
|
|
This week, I rebuilt my housing-price model from scratch and explored how collaborative filtering predicts outcomes beyond movie ratings
|
|
0
|
55
|
October 25, 2026
|
|
This week, I tested whether equal-weight ensembles of my random forest, linear model, & neural network could beat my best housing-price model; none did. Next, I’m rebuilding the workflow from memory before moving on to collaborative filtering
|
|
0
|
71
|
October 18, 2026
|
|
This week, I built a linear model and neural network to predict real-estate prices on an unfamiliar dataset. Along the way, I fixed mismatched error metrics and inconsistent feature scaling, and learned to rebuild/explain the workflow on my own
|
|
4
|
144
|
October 16, 2026
|
|
This week, I trained a random forest with 25% lower error than my linear housing-price model on the same validation set. Then I used maps and feature importance to explore what it had learned about location and transit access
|
|
0
|
88
|
October 11, 2026
|
|
This week, I built and tested linear-model and neural-network ensembles to predict real-estate prices. Both had lower validation error than their members’ average, but neither beat its best individual model
|
|
0
|
99
|
October 3, 2026
|
|
I finished first working versions of both fastai Chapter 4 assignments. I still need the code open beside me
|
|
2
|
162
|
September 25, 2026
|
|
After six hours of waiting for my NLP classifier to train, it never finished; I cut the sample size way down, ran it again, and finished in a few minutes. In the future, I'll start with a smaller sample size and add more samples as needed
|
|
3
|
118
|
September 23, 2026
|
|
This week, I trained a movie-review classifier to 94% training accuracy this week, using a sample of reviews from IMDB. Turns out, I was using a pretrained model without knowing it
|
|
0
|
99
|
September 13, 2026
|
|
I rebuilt the training process for my MNIST classifier from scratch and caught a bug: the optimizer was using the wrong model’s parameters. After several weeks on fastai’s Lesson 3, I understand how the pieces fit together and am ready to move on to NLP
|
|
0
|
103
|
September 7, 2026
|
|
I got stuck rebuilding fastai's Learner
|
|
0
|
89
|
August 24, 2026
|
|
How do you handle large image dataset collection and refresh?
|
|
0
|
83
|
August 21, 2026
|
|
Gradient descent finally clicked
|
|
0
|
91
|
August 17, 2026
|
|
Cloud GPU services vs having your own, which is better for AI?
|
|
8
|
6834
|
August 13, 2026
|
|
I built a neural network in Excel
|
|
0
|
86
|
August 10, 2026
|
|
**I built three fastai apps this past week**
|
|
0
|
77
|
August 3, 2026
|
|
I stopped guessing the learning rate
|
|
0
|
71
|
July 27, 2026
|
|
How to handle overfitting when training a CNN on small custom image datasets?
|
|
1
|
120
|
July 14, 2026
|
|
Text2LIVE: Text-Driven Layered Image and Video Editing
|
|
8
|
1506
|
June 24, 2026
|
|
Implementing Self Attention from scratch using Pytorch
|
|
2
|
351
|
May 2, 2026
|
|
How Should AI Respond in Moments That Matter?
|
|
0
|
91
|
April 7, 2026
|
|
98.7% accuracy on bitcoin price prediction?
|
|
18
|
14282
|
April 2, 2026
|
|
Auto grading exams using deep learning?
|
|
5
|
1039
|
March 6, 2026
|
|
Hard-mish activation function
|
|
9
|
5637
|
March 2, 2026
|
|
Super-Resolution to improve models
|
|
5
|
1752
|
February 15, 2026
|
|
Vision_Tabular: Simple Hybrid (Image + Tabular) Models for FastAI V2
|
|
0
|
107
|
January 12, 2026
|
|
Deep learning library book
|
|
4
|
225
|
January 6, 2026
|
|
Efficient finetuning of Llama 3 with FSDP QDoRA – Answer.AI
|
|
2
|
202
|
December 21, 2025
|