All Questions

8,467 questions with no answers
Filter by
Sorted by
Tagged with
22 votes
0 answers
3k 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 ...
user avatar
9 votes
0 answers
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 ...
  • 199
9 votes
0 answers
2k 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. ...
  • 91
8 votes
0 answers
1k views

Find missing object(s) in image with a priori knowledge about the missing object(s) (w.r.t base image)

Problem Statement: I am working on developing a method, or borrow/modify/combine existing ones, where given an golden image (reference or base with all expected objects to be present), it is able to ...
  • 4,076
8 votes
0 answers
816 views

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

I am using the gensim library for topic modeling, more specifically LDA. I created my corpus, my dictionary, and my LDA model. With the help of the pyLDAvis library I visualized the results. When I ...
8 votes
0 answers
109 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 ...
  • 101
8 votes
0 answers
182 views

How to predict advantage value in deep reinforcement learning

I'm currently working on a collection of reinforcement algorithms: https://github.com/lhk/rl_gym For deep q-learning, you need to calculate the q-values that should be predicted by your network. There ...
  • 181
8 votes
0 answers
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 ...
  • 81
7 votes
0 answers
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-...
  • 696
7 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. ...
7 votes
0 answers
1k views

Multivariate, multistep forecasting with LSTM

I want to use an RNN with LSTM to forecast multiple steps into the future, based on multiple inputs. I have some ideas for different ways to approach this, but I'm afraid I'm missing the "right way" ...
  • 171
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 ...
  • 71
7 votes
0 answers
882 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 ...
7 votes
0 answers
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 ...
  • 1,087
7 votes
0 answers
506 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 = ...
  • 1,327
6 votes
0 answers
100 views

How Exactly Does In-Context Few-Shot Learning Actually Work in Theory (Under the Hood), Despite only Having a "Few" Support Examples to "Train On"?

Recent models like the GPT-3 Language Model (Brown et al., 2020) and the Flamingo Visual-Language Model (Alayrac et al., 2022) use in-context few-shot learning. The models are able to make highly ...
6 votes
0 answers
48 views

How sklearn SVM find the initial hyperplane before Optimisation?

The optimization goal of the SVM is to maximize the distance between the positive and negative hyperplanes. But before optimizing, how sklearn first find the positive and negative support vectors and ...
6 votes
0 answers
121 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 ...
6 votes
0 answers
167 views

What does big O mean in KNN optimal weights?

Wiki gives this definition of KNN In pattern recognition, the k-nearest neighbors algorithm (k-NN) is a non-parametric method used for classification and regression. In both cases, the input consists ...
  • 584
6 votes
0 answers
298 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=...
6 votes
0 answers
69 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 ...
  • 231
6 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 ...
6 votes
0 answers
2k views

What is the minimum number of times a word needs to appear in word2vec training corpus for quality results?

When training a word2vec model with, eg, gensim, you can specify the minimum times a word needs to be seen (with the parameter min_count). The default value for this seems to be 5. Are there any ...
6 votes
0 answers
258 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{...
6 votes
0 answers
349 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 ...
  • 61
6 votes
0 answers
86 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 ...
6 votes
0 answers
109 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\...
6 votes
0 answers
585 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 ...
6 votes
0 answers
220 views

Connect output node to next hidden node in RNN

I'm trying to build a neural network with an unconventional architecture and a having trouble figuring out how. Usually we have connections like so, where $X=$ input, $H=$ hidden layer, $Y=$ output ...
  • 2,158
6 votes
0 answers
2k views

How to tune weights in Voting Classifier (Sklearn)

I am trying to do the following: ...
6 votes
0 answers
1k 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 ...
  • 61
6 votes
0 answers
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 ...
6 votes
0 answers
103 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 ...
6 votes
0 answers
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: ...
6 votes
0 answers
281 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 ...
  • 161
6 votes
0 answers
99 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 ...
6 votes
0 answers
308 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). ...
  • 775
5 votes
0 answers
61 views

How is image convolution actually implemented in deep learning libraries using simple linear algebra?

As a clarifier, I want to implement cross-correlation, but the machine learning literature keeps referring to it as convolution so I will stick with it. I am trying to implement image convolution ...
5 votes
0 answers
619 views

sklearn FutureWarning message when running a CNN model

When I run my model, I am receiving the following error message: ...
  • 135
5 votes
0 answers
2k views

Dealing with categorical variables in Isolation Forest

Isolation Forest is widely used when dealing with outlier/anomaly detection when we have no labels. The theory behind is that making random split at random points and counting how many splits you do ...
5 votes
0 answers
924 views

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

My program gives the following error message: ...
  • 163
5 votes
0 answers
204 views

Can I turn any binary classification algorithms into multiclass algorithms using softmax and cross-entropy loss?

Softmax + cross-entropy loss for multiclass classification is used in ML algorithms such as softmax regression and (last layer of) neural networks. I wonder if this method could turn any binary ...
4 votes
0 answers
51 views

Does ROC AUC different between crossval and test set indicate overfitting or other problem?

I am training a composite model (XGBoost, Linear Regression, and RandomForest) to predict injured people probability. Well, the results of cross-validation with 5 folds. Well, I can see any problem ...
4 votes
0 answers
30 views

Best practices for scaling data science / engineering teams

I am trying to find best practices for scaling data science teams, i.e find an efficient workflow/methodology to divide work between Software Engineers and Researchers working on a same product. I’...
  • 141
4 votes
0 answers
1k views

How to train continuous/soft classification model?

The classic classification problem is like finding the function $F:\mathbb{R}^n\mapsto \{0,1\}$. The label set will be [Apple,Banana,Banana,...,Apple]. What if I want to train a function $F:\mathbb{R}...
  • 4,156
4 votes
0 answers
2k views

Why does Position Embeddings work?

In the papers "Convolutional Sequence to Sequence Learning" and "Attention Is All You Need", positions embeddings are simply added to the input words embeddings to give the model a sense of the order ...
  • 1,305
4 votes
0 answers
59 views

Image grid - labels?

I was wondering if labels could be visualized below images in the image grid tool in Image Analytics? I know, this feature might be not terribly useful for images in general, hence unlikely to be ...
  • 41
3 votes
0 answers
96 views

Zero-shot learning for tabular data?

Can anyone point me to methods for zero-shot learning on tabular data? There is some very cool work being done for zero-shot learning on images and text, but I'm struggling to find work being done to ...
3 votes
0 answers
31 views

Can we recognize different events in time-series data by patterns?

I'm currently have to deal with multiple time-series datasets with the same type of patterns. My quest is to find a way to label these data points (or may be intervals) correctly. Below is how the ...
3 votes
0 answers
38 views

Understanding Kneser-Ney Formula for implementation

I am trying to implement this formula in Python $$ \frac{\text{max}(c_{KN}(w^{i}_{i-n+1} - d), 0)}{c_{KN}(w^{i-1}_{i-n+1})} + \lambda(c_{KN}(w^{i-1}_{i-n+1})\mathbb{P}(c_{KN}(w_{i}|w^{i-1}_{i-n+2})$$ ...
  • 237

15 30 50 per page
1
2 3 4 5
170