Unanswered Questions

7,795 questions with no upvoted or accepted answers
15
votes
0answers
879 views

Visualization of multiple Markov models

I am working on a project where we compare over 10 different Markov models, each representing a different treatment plan. Most often single models are visualized with a decision tree or transition ...
12
votes
3answers
605 views

XGBoost outputs tend towards the extremes

I am currently using XGBoost for risk prediction, it seems to be doing a good job in the binary classification department but the probability outputs are way off, i.e., changing the value of a feature ...
10
votes
2answers
4k views

Catboost Categorical Features Handling Options (CTR settings)?

I am working with a dataset with large number of categorical features (>80%) predicting a continuous target variable (i.e. Regression). I have been reading quite a bit about ways to handle categorical ...
8
votes
1answer
77 views

Features reduction for the not correlated data set

I am working with classification problem on a training data set, which have 100 features. All the features in pairs haven't visible correlation. One can see it in the example pair plot for the some of ...
8
votes
1answer
483 views

Differences between gradient calculated by different reduction methods in PyTorch

I'm playing with different reduction methods provided in built-in loss functions. In particular, I would like to compare the following. The averaged gradient by performing backward pass for each loss ...
8
votes
1answer
503 views

Load keras model in Java

What are the requirements to load the trained model by Keras in Java? I checked that DeepLearning4J supports ...
8
votes
1answer
165 views

Improve NER label results on Non-English text

I am working on some Medieval Latin text and was using various methods of NER such as CLTK (Latin Model), Spacy (Multilingual, Italian, Spanish Model) and StanfordNER (Spanish Model). When I used the ...
8
votes
0answers
581 views

What is the difference between fasttext and DANs in document classification?

I came across two interesting papers that describe promising approaches for document classification using word embedding. 1. The fasttext algorithm Described in the paper Bag of Tricks for ...
7
votes
0answers
141 views

Formal proof of vanilla policy gradient convergence

So I stumbled upon this question, where the author asks for a proof of vanilla policy gradient procedures. The answer provided points to some literature, but the formal proof is nowhere to be included....
7
votes
0answers
250 views

How to arrange the dataset/images for CNN+LSTM

I am working on an image classification problem using Transfer Learning with Resnet50 as base model (in Keras) (For example Class A and Class B). There is a time factor involved in this ...
7
votes
0answers
704 views

Understanding Timestamps and Batchsize of Keras LSTM considering Hiddenstates and TBPTT

What I'm trying to do What I am trying to do is predicting the next data-point $x_t$ for each point in the timeseries $[x_0, x_1, x_2,...,x_T]$ in the context of a date-stream in real-time, in theory ...
7
votes
2answers
126 views

Representing similar states in reinforcement learning?

Let's say I'd like to design a Q learning algorithm that learns to play poker. The number of different possible States is very large, but a lot are very similar: for example, if the initial state ...
7
votes
1answer
134 views

Synthetic Gradients good number of Layers & neurons

I would like to train my LSTM with a "synthetic gradients" Decoupled Neural Interface (DNI). How to decide on the number of layers and neurons for my DNI? Searching them by trial end error or ...
7
votes
5answers
442 views

What are some of the best practices for sharing data and models with colleagues?

As a data scientist who recently joined a new team, I wanted to ask the community how they share data and models among their colleagues. Currently I have to resort to storing data in some central ...
7
votes
0answers
322 views

ngram and RNN prediction rate wrt word index

I tried to plot the rate of correct predictions (for the top 1 shortlist) with relation to the word's position in sentence : I was expecting to see a plateau sooner on the ngram setup since it ...

15 30 50 per page