All Questions

8,420 questions with no answers
Filter by
Sorted by
Tagged with
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 ...
Matt's user avatar
  • 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. ...
AfBM's user avatar
  • 91
8 votes
0 answers
120 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 ...
Phaune's user avatar
  • 101
8 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 ...
Reward's user avatar
  • 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-...
Harman's user avatar
  • 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. ...
AutomaKen's user avatar
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" ...
Aurast's user avatar
  • 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 ...
Varun's user avatar
  • 71
7 votes
0 answers
913 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 ...
anymous.asker's user avatar
7 votes
0 answers
508 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 = ...
ihadanny's user avatar
  • 1,347
6 votes
0 answers
128 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 ...
user87590's user avatar
6 votes
0 answers
322 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=...
Johan Gras's user avatar
6 votes
0 answers
76 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 ...
Jor_El's user avatar
  • 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 ...
Palisadoes's user avatar
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 ...
user1253952's user avatar
6 votes
0 answers
279 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{...
user3326682's user avatar
6 votes
0 answers
362 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 ...
Jason's user avatar
  • 61
6 votes
0 answers
91 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 ...
John Karimov's user avatar
6 votes
0 answers
124 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\...
David Silver's user avatar
6 votes
0 answers
599 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 ...
ethelion's user avatar
6 votes
0 answers
225 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 ...
tom's user avatar
  • 2,188
6 votes
0 answers
3k views

How to tune weights in Voting Classifier (Sklearn)

I am trying to do the following: ...
Abhinav Gupta's user avatar
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 ...
Daniel Underwood's user avatar
6 votes
0 answers
107 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 ...
Jan Wrona's user avatar
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: ...
user1877600's user avatar
6 votes
0 answers
287 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 ...
Shindou's user avatar
  • 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 ...
André Soares's user avatar
6 votes
0 answers
332 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). ...
Minu's user avatar
  • 795
5 votes
0 answers
80 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 ...
Jozef Nagy's user avatar
5 votes
0 answers
730 views

sklearn FutureWarning message when running a CNN model

When I run my model, I am receiving the following error message: ...
Jack's user avatar
  • 145
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 ...
Carlos Mougan's user avatar
5 votes
0 answers
1k views

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

My program gives the following error message: ...
Kehrwert's user avatar
  • 163
4 votes
0 answers
137 views

How Does the Reward Model in ChatGPT Calculate Losses?

Reading the InstructGPT paper(which seems to be what ChatGPT was built off of), I found this equation for the reward function. However, I'm struggling to understand how this equation is used to ...
itisyeetimetoday's user avatar
4 votes
0 answers
55 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 ...
GregOliveira's user avatar
4 votes
0 answers
202 views

ResNet50 + Transformer

In many papers people extract features from image using ResNet and than pass them through transformer. I want to implement the same. I want to get features and than classify them using transformer. ...
alex-uarent-alex's user avatar
4 votes
0 answers
161 views

Bag of words: Prediction on new (out-of-sample) data

I'm working with a bag of words in R: library(tm) corpus = VCorpus(textsource) dtm = DocumentTermMatrix(corpus) dtm = as.matrix(dtm) I use the matrix ...
Peter's user avatar
  • 7,247
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}...
Icyblade's user avatar
  • 4,226
4 votes
0 answers
60 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 ...
Sal9K's user avatar
  • 41
3 votes
0 answers
51 views

Public data set with exciting data

I'm going to give a talk about a tool for viewing tabular datasets. I'll first give this talk at a meetup, then hopefully at a series of conferences over the next few years. I want to demonstrate to ...
Ram Rachum's user avatar
3 votes
0 answers
3k views

What are the "EMA" weights included with certain pre-trained models?

I came across this machine learning model called "Stable Diffusion v1." When downloading the pre-trained weights for this model, I noticed that there's a couple of different files: ...
Trevor Sullivan's user avatar
3 votes
0 answers
208 views

Why is NDCG high even for wrongly ranked predictions?

The NDCG (Normalized Discounted Cumulative Gain) metric for ranking is defined as DCG/IDCG, where IDCG is the ideal DCG and is said to take values in [0, 1]. However, since the DCG will always be ...
Michael's user avatar
  • 131
3 votes
0 answers
35 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 ...
duy quan duc's user avatar
3 votes
0 answers
48 views

Understanding Kneser-Ney Formula for implementation

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

Is it Scientifically Rigorous to create a multimodal ML Model with data from multiple sources

I'm attempting to create a multimodal machine learning model for disease diagnosis. However, I'm having quite a bit of difficulty finding public data sets with all the data I need. For example, I need ...
Pulkith Paruchuri's user avatar
3 votes
0 answers
18 views

Homework/class help: Backward propagation of max pooling if each element in an array determines more than one value?

(This isn't actually my homework, and in fact wasn't addressed in my homework, but I was confused about this because my homework hadn't addressed this) For example if I have an array: And I do max ...
user127418's user avatar
3 votes
0 answers
1k views

Identify MCAR, MNAR and MAR in the data

If I have missing values in a dataset, I can't just blindly impute them with mean/median/mode or any other technique. I have to identify what kind of missing values they are, namely: MCAR (missing ...
spectre's user avatar
  • 1,576
3 votes
0 answers
180 views

Why margin loss is used in Capsule Network instead of Cross Entropy loss?

I'm reading the Capsule Network paper proposed by Hinton. I'm not sure why the margin loss is used instead of the cross entropy loss. Any intuitive explaination for this?
xtiger's user avatar
  • 131
3 votes
0 answers
125 views

Non-greedy decision tree / random forest implementation(s) in Python

The standard random forest is trained using a greedy approach for computational feasibility. However, there are a number of alternative methods such as "lookahead" or using bilevel ...
Peter's user avatar
  • 7,247
3 votes
0 answers
839 views

Forecast Model to Estimate Customer Service Call Volume and Appropriate Staff

I am working on a project to predict the proper staffing needed for a customer service team using historical data. I am new to machine learning, and I am not sure if my approach to this problem is the ...
Tony's user avatar
  • 31
3 votes
0 answers
30 views

How to train a neural network where computing the loss requires multiple object values?

I want to train a function that given metadata about an image produces hyper-parameters for an algorithm which operates on the image. My understanding is (please forgive me I'm a novice here) a neural ...
Jonathan Woollett-light's user avatar

15 30 50 per page
1
2 3 4 5
169