Unanswered Questions
9,496 questions with no upvoted or accepted answers
15
votes
0
answers
3k
views
Python : Feature Matching + Homography to find Multiple Objects
I'm trying to use OpenCV via Python to find multiple objects in a train image and match it with the key points detected from a query image. For my case, I'm trying to detect the tennis courts in the ...
12
votes
0
answers
212
views
Training value neural network AlphaGo style
I have been trying to replicate the results obtained by AlphaGo following their supervise learning protocol. The papers specify that they use a network that has two heads: a value head that predicts ...
- 783
8
votes
1
answer
110
views
How can I measure the similarity between distance matrices during embedding training?
I am studying how the distances between embeddings evolve during training of a language model.
One way to describe this "evolution" is that the k-nearest neighbours of a particular embedding ...
CommunityBot
- 1
8
votes
0
answers
65
views
How does SciPy's linkage() calculate centroid from pairwise distances?
I am learning about hierarchical clustering from SciPy's linkage documentation (which is much more understandable than the Wikipedia page.
Some of the cluster ...
- 625
8
votes
0
answers
3k
views
Tensorflow v1 Dataset API AttributeError with ndim
I'd like to make pipeline for optimizing Gpu and Cpu.
Dataset
It's about 10000 datapoint and 4 description variables for the regression problem.
...
- 201
8
votes
0
answers
2k
views
Using the Python Keras multi_gpu_model with LSTM / GRU to predict Timeseries data
I'm having an issue with python keras LSTM / GRU layers with multi_gpu_model for machine learning.
When I use a single GPU, the predictions work correctly ...
- 181
7
votes
0
answers
62
views
Media Value Simulation ( Regression)
I am estimating a regression model to predict media value and later use residuals for Monte Carlo simulation.
The model includes:
Market fixed effects (grouped)
Asset categories
A hierarchical ...
- 8,546
7
votes
0
answers
39
views
Addressing Variable Observation Counts in Event-Driven Forecasting (2026 Projection)
I am transitioning from a Geometric Brownian Motion framework, where time steps are fixed, to an event-driven modeling approach using bootstrap methods.
In GBM or classical time series models, the ...
- 151
7
votes
0
answers
49
views
Prediction Result is Strange
I am currently building a Gradient boosting regressor model using panel data including year, socio-demographic (such as population), climate (such as temperature), and economic (such as GDP) as a ...
- 745
7
votes
0
answers
169
views
Unable to transform (greatly performing) Autoencoder into Variational Autoencoder
Following the procedure described in this SO question, I am trying to transform my (greatly performing) convolutional Autoencoder into a Variational version of the same Autoencoder. As explained in ...
- 71
7
votes
0
answers
2k
views
Fine tuning accuracy lower than Raw Transfer Learning Accuracy
I've used transfer learning on Inception V3 with ImageNet weights on Keras with Tensorflow backend on python 2.7 to create an image classifier. I first extracted and saved the bottleneck features from ...
- 24.8k
7
votes
0
answers
986
views
ALS in Spark: what loss function is it minimizing?
I’ve playing with the MovieLens ratings dataset under Spark’s ALS and a manual implementation of ALS and comparing results with the same hyperparameters. I’d like to know this exactly in order to make ...
- 894
7
votes
0
answers
549
views
differences between LSQR and FTRL when working with very sparse data
I have a 2M instances dataset with millions of very very sparse dummy variables created using the hashing trick = ...
- 4,523
7
votes
2
answers
580
views
When to use which multiple testing correction?
There are a large number multiple testing p-value correction methods. e.g.:
...
CommunityBot
- 1
6
votes
0
answers
107
views
What makes XGBoost so much more dominant with structured data?
XGBoost has a history of being dominant in Kaggle competitions, but why is it so competitive on structured data compared to other ML algorithms?
I’ve read that sparse matrix utilization improves the ...
- 693