All Questions

6,624 questions with no answers
Filter by
Sorted by
Tagged with
18
votes
0answers
352 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....
14
votes
0answers
2k 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
0answers
1k views

AdaBoost implementation and tuning for high dimensional feature space in R

I am trying to implement the AdaBoost.M1 algorithm (trees as base-learners) to a data set with a large feature space (~ 20.000 features) and ~ 100 samples in R. ...
6
votes
0answers
175 views

Are there any graph embedding algorithms like this already?

I wrote an algorithm for generating node embeddings based on the graph's topology. Most of the explanation is done in the readme file and the examples. The question is: Am I reinventing the wheel? ...
6
votes
0answers
2k views

Why is my Keras model not learning image segmentation?

Edit: as is turns out, not even the model's initial creator could successfully fine-tune it. This is most likely a problem of implementation, or possibly related to the non-intuitive way in which the ...
6
votes
0answers
2k 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 ...
6
votes
0answers
1k views

Comparing transition matrices for Markov chains

I have a population, each unit of which exists in one of several states that change over time. I am using first-order Markov chains to model these state transitions. My population can be segmented ...
5
votes
0answers
364 views

XGBoost custom objective for regression in R

I implemented a custom objective and metric for a xgboost regression task. In order to see if I'm doing this correctly, I started with a quadratic loss. The ...
5
votes
0answers
522 views

Gensim LDA model: return keywords based on relevance (λ - lambda) value

I am using gensim library for topic modeling, more specifically LDA. I have created my corpus, my dictionary and my lda model, and with the help of pyLDAvis library I visualize the results. When I ...
5
votes
0answers
9k views

How is WordPiece tokenization helpful to effectively deal with rare words problem in NLP?

I have seen that NLP models such as BERT utilize WordPiece for tokenization. In WordPiece, we split the tokens like playing to play and ##ing. It is mentioned that it covers a wider spectrum of Out-Of-...
5
votes
0answers
2k 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. ...
5
votes
0answers
63 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 ...
5
votes
0answers
757 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 ...
5
votes
0answers
484 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
votes
0answers
211 views

1D CNN Variational Autoencoder Conv1D Size

I am trying to create a 1D variational autoencoder to take in a 931x1 vector as input, but I have been having trouble with two things: Getting the output size of 931, since maxpooling and upsampling ...
4
votes
0answers
47 views

Can we use embeddings or latent vectors for a recommender system?

I'm having a hard time understanding why people use any vector they find as a candidate for a recommender system. In my mind, a recommender system requires a space where distance represents similarity....
4
votes
0answers
71 views

Repeated k-fold Cross Validation for time series data?

I have a relative small sample size (330 with 45 features) + it's time series data. I want to train my LightGBM regression model for best generalized RMSE score and want to use repeated CV. I use ...
4
votes
0answers
213 views

How to use multiple text features for NLP classifier?

I am trying to build text classifier, Usually, we have one text column and ground truth. But I am working on a problem where dataset contains many text features. I am exploring different ways how to ...
4
votes
0answers
277 views

How to detect vanishing and exploding gradients with Tensorboard?

I have two "sub-questions" 1) How can I detect vanishing or exploding gradients with Tensorboard, given the fact that currently write_grads=True is deprecated in the Tensorboard callback as per "un-...
4
votes
0answers
675 views

Tensorflow, Optimizer.apply_gradient: 'NoneType' object has no attribute 'merge_call'

My program gives the following error message: ...
4
votes
0answers
457 views

Why does degradation occur in deep neural networks?

It has been shown that "plain" neural networks tend to have an increased amount training error, and accompanied test error, as more layers are added. I am not quite certain as to why this occurs. In ...
4
votes
0answers
232 views

Optimal implementation of vanilla DQN loss in Keras

I've implemented vanilla DQN for continuous/non-images (no CNN) states in keras. But, I'm not sure if my implementation of the loss computation is optimal. For reminder the loss is defined as : $loss=...
4
votes
0answers
55 views

Fitting model to differenced time series

I have a time series on daily stock price of company(2013 data points).I took a first order difference and the following acf and pacf plots of the differenced series were obtained. However, I am ...
4
votes
0answers
1k 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 ...
4
votes
0answers
502 views

Metrics to evaluate features' importance in classification problem (with random forest)

I want to evaluate the importance of each of the features of a 2000x60 dataset in a classification problem with random forest. The most widely used ones apparrently are: Cross Entropy-Information ...
4
votes
0answers
3k views

Isolation Forest Feature Importance

As of scikit-learn version 0.19.1, there is no implementation for calculating feature importance in an Isolation Forest. I'm also having trouble finding any online resources proposing ways to get at ...
4
votes
0answers
1k views

Preparing ground truth labels for YOLO3

I want to train YOLO3 for a custom dataset that has raw labels in JSON format. Each bounding box in JSON is specified as [x1, y1, x2, y2]. So far, I have ...
4
votes
0answers
307 views

Multiple activation functions with TensorFlow estimator DNNClassifier

I just want to know if is it possible to use tf.estimator.DNNClassifier with multiple different activation functions. I mean, could I use a DNNClassifier estimator which use different activation ...
4
votes
0answers
203 views

Confidence value in AdaBoost?

I read this introduction about AdaBoost (http://www.cs.man.ac.uk/~nikolaon/~nikolaon_files/Introduction_to_AdaBoost.pdf), and am curious why confidence for each model is defined as $$\alpha_j=\frac{...
4
votes
0answers
294 views

Maths of Xavier initialization

The paper I read is Glorot et al (2010). And the math part is in Section 4.2.1. Formula (5) and (10) make sense to me but I cannot derive formula (6) and (7) myself from (2) and (3). I found many ...
4
votes
0answers
74 views

Classify driver based on time-series sensor data

I want to build a model that can detect which driver is driving now the car based on a dataset that contains 20 driver records for 3600s each driver ( the dataset contains all the car sensors values ...
4
votes
0answers
74 views

Learning a logical function with a 2 layer BDN network - manual weight setting rule question?

So I am trying to construct a 2-layer network of binary decision neurons as proposed by McCullough and Pitts (1943) to learn a logical function (a composition of AND's and OR's) such as: $((\neg x_1\...
4
votes
0answers
1k 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 ...
4
votes
0answers
3k views

Kalman filter for time series prediction

I have the information about the behaviour of 400 users across period of 1 months (30 days). Across those 30 days I measure 4 different information (let's call it A,B,C and D), hence I have a total of ...
4
votes
0answers
566 views

Adversarial Learning for Semantic Segmentation

I am incorporating Adversarial Training for Semantic Segmentation from Adversarial Learning for Semi-Supervised Semantic Segmentation. The idea is like this: The discriminator takes as input a ...
4
votes
0answers
2k views

How to tune weights in Voting Classifier (Sklearn)

I am trying to do the following: ...
4
votes
0answers
1k views

In XGBoost, how to change eval function and keeping same objective?

I want to keep objective as "reg:linear" and eval_metric as customised rmse as follows. ...
4
votes
0answers
776 views

How does XGBoost compute the probabilities in predict_proba()?

I'm using the sklearn wrapper for XGBoost. I didn't manage to find a clear explanation for the way the probabilities given as output by predict_proba() are computed. In random forest for example, I ...
4
votes
0answers
98 views

Quantifying 'growth friction' when projecting target goals

As part of my DS work I spend some fraction of my time helping the team make growth projections, either for setting growth targets or when forecasting actual data. There is obviously a range of ways ...
4
votes
0answers
1k views

Keras objective function shared between outputs

Is there any way to implement a loss function that is shared between outputs? I have a 2D image output and scalar classification that are both used by a single loss function. I have attempted writing ...
4
votes
0answers
95 views

Fixed-radius range search in non-Euclidean space

I'm trying to find an indexing data structure most suitable for my metric space: set of IP network related data (IP addresses, ports, TCP flags, ...), distance function is continuous, non-Euclidean ...
4
votes
0answers
11k views

Tuning Gradient Boosted Classifier's hyperparametrs and balancing it

I am not sure if it is a correct stack. Maybe I should have put my question into crossvalidated. Nevertheless, I perform following steps to tune the hyperparameters for a gradient boosting model: ...
4
votes
0answers
268 views

how to propagate error from convolutional layer to previous layer?

I've been trying to implement a simple convolutional neural network. But I've been stuck at this problem for over a week. To be specific, assume there are 3 layers in a convolutional pass, marked as ...
4
votes
0answers
90 views

Meta-analysis of public 16S data

I am trying to start a meta-analysis for which I want to extract some 16S-based information from public databases. Moreover, I want to relate this information with any metadata found in the associated ...
4
votes
0answers
268 views

3D map using leaflet

I'm trying to create 3D bars on this map. Can anyone please advise if this is possible, and how? http://leafletjs.com/examples/choropleth.html My data: UFO sightings in the USA (location wise). ...
3
votes
0answers
25 views

Negative learning implementation in pytorch

I have read a paper on Negative Learning: https://arxiv.org/abs/1908.07387. The idea is that you can train a network not only by telling what label of the sample is, but by telling what it surely is ...
3
votes
0answers
25 views

Using softmax for multilabel classification (as per Facebook paper)

I came across this paper by some Facebook researchers where they found that using a softmax and CE loss function during training led to improved results over sigmoid + BCE. They do this by changing ...
3
votes
0answers
51 views

Unbiasedness of random forests

Suppose that I am trying to build a random forest by subsampling the data and choosing a single feature per tree randomly. For example, suppose there is some dataset, $D = \{(x_{1},y_{1}), ......(x_{N}...
3
votes
0answers
34 views

Finding the position of an arbitrary object in a static image?

One common object detection scenario involves finding trained models in an arbitrary scene. For example, we can train a model to understand what a "bicycle" looks like, by providing various ...
3
votes
0answers
96 views

What are the 'protos' in TF Object Detection?

I am struggling to understand what are the 'protos' in TF Object Detection? Why do we need them here? Also, while setting up the TF API we need to download and compile protocol buffers. There is also ...

15 30 50 per page
1
2 3 4 5
133