|
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
|
21
|
October 3, 2026
|
|
Getting The Bing Image Search key
|
|
135
|
39521
|
September 29, 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
|
|
0
|
31
|
September 27, 2026
|
|
I finished first working versions of both fastai Chapter 4 assignments. I still need the code open beside me
|
|
2
|
109
|
September 25, 2026
|
|
Please improve forum post regulation
|
|
2
|
128
|
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
|
55
|
September 23, 2026
|
|
Beginner: Setup ✅
|
|
248
|
51000
|
September 21, 2026
|
|
Error: expected input to have 3 channels, but got 1 channel instead
|
|
1
|
62
|
September 15, 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
|
57
|
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
|
63
|
September 7, 2026
|
|
Error while importing fastai.vision.all in vast.ai
|
|
0
|
76
|
September 6, 2026
|
|
Using deeplearning model for inference
|
|
7
|
317
|
September 4, 2026
|
|
FBFS - Fast Bunnies Friday Sessions (Study Group 2024)
|
|
10
|
1589
|
September 4, 2026
|
|
Admin : Please Take Action on Spam
|
|
0
|
59
|
September 3, 2026
|
|
Beginner: Using Colab or Kaggle ✅
|
|
196
|
27864
|
August 28, 2026
|
|
Building deep learning workstation for $2200
|
|
28
|
13125
|
August 28, 2026
|
|
AI workstation setup?
|
|
9
|
2203
|
August 28, 2026
|
|
Project: multi-country price intelligence dashboard — from scraping to fine-tuned classifier (course project writeup)
|
|
1
|
81
|
August 26, 2026
|
|
Introduce yourself here
|
|
321
|
14002
|
August 24, 2026
|
|
I got stuck rebuilding fastai's Learner
|
|
0
|
62
|
August 24, 2026
|
|
What is your practical workflow for refreshing image-text data?
|
|
0
|
48
|
August 22, 2026
|
|
How do you handle large image dataset collection and refresh?
|
|
0
|
52
|
August 21, 2026
|
|
Gradient descent finally clicked
|
|
0
|
67
|
August 17, 2026
|
|
Cloud GPU services vs having your own, which is better for AI?
|
|
8
|
6741
|
August 13, 2026
|
|
Share your work here ✅
|
|
2007
|
190720
|
August 11, 2026
|
|
I built a neural network in Excel
|
|
0
|
64
|
August 10, 2026
|
|
Huggingface space free Gradio is paid now
|
|
0
|
112
|
August 5, 2026
|
|
[Lesson 1] Bird/Forest classifier predicts "Bird" for unrelated images
|
|
1
|
105
|
August 5, 2026
|
|
**I built three fastai apps this past week**
|
|
0
|
55
|
August 3, 2026
|
|
I stopped guessing the learning rate
|
|
0
|
54
|
July 27, 2026
|