|
About the Deep Learning category
|
|
36
|
8932
|
May 30, 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
|
17
|
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
|
90
|
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
|
31
|
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
|
64
|
October 3, 2026
|
|
I finished first working versions of both fastai Chapter 4 assignments. I still need the code open beside me
|
|
2
|
135
|
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
|
82
|
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
|
75
|
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
|
76
|
September 7, 2026
|
|
I got stuck rebuilding fastai's Learner
|
|
0
|
71
|
August 24, 2026
|
|
How do you handle large image dataset collection and refresh?
|
|
0
|
61
|
August 21, 2026
|
|
Gradient descent finally clicked
|
|
0
|
76
|
August 17, 2026
|
|
Cloud GPU services vs having your own, which is better for AI?
|
|
8
|
6766
|
August 13, 2026
|
|
I built a neural network in Excel
|
|
0
|
71
|
August 10, 2026
|
|
**I built three fastai apps this past week**
|
|
0
|
59
|
August 3, 2026
|
|
I stopped guessing the learning rate
|
|
0
|
58
|
July 27, 2026
|
|
How to handle overfitting when training a CNN on small custom image datasets?
|
|
1
|
105
|
July 14, 2026
|
|
Text2LIVE: Text-Driven Layered Image and Video Editing
|
|
8
|
1491
|
June 24, 2026
|
|
Implementing Self Attention from scratch using Pytorch
|
|
2
|
317
|
May 2, 2026
|
|
How Should AI Respond in Moments That Matter?
|
|
0
|
87
|
April 7, 2026
|
|
98.7% accuracy on bitcoin price prediction?
|
|
18
|
14176
|
April 2, 2026
|
|
Auto grading exams using deep learning?
|
|
5
|
1019
|
March 6, 2026
|
|
Hard-mish activation function
|
|
9
|
5615
|
March 2, 2026
|
|
Super-Resolution to improve models
|
|
5
|
1738
|
February 15, 2026
|
|
Vision_Tabular: Simple Hybrid (Image + Tabular) Models for FastAI V2
|
|
0
|
98
|
January 12, 2026
|
|
Deep learning library book
|
|
4
|
210
|
January 6, 2026
|
|
Efficient finetuning of Llama 3 with FSDP QDoRA – Answer.AI
|
|
2
|
186
|
December 21, 2025
|
|
Video modeling, identifying speaker
|
|
1
|
329
|
December 8, 2025
|
|
End to End speaker recognition system
|
|
2
|
1254
|
December 8, 2025
|
|
How to calculate derivative of matrix with respect to other matrix dZ/dW?
|
|
1
|
144
|
October 29, 2025
|