### off-policy evaluation in reinforcement learning

IPS estimator, which is used for off-policy evaluation in a contextual bandit problem, is well explained here: Doubly Robust Policy Evaluation andOptimization https://arxiv.org/pdf/1503.02834.pdf The old policy $\mu$, or the behavior policy, is okay to be non-stationary in the IPS estimator even if the new policy $\nu$, or the target policy, should be stationary. I wonder…

### EEG and Accelerometer Neural Network

I have frequency EEG data from fall and non-fall events and I am trying to incorporate it with accelerometer data that was collected at the same time. One approach is, of course, to use two separate algorithms and find the threshold for each. Then comparing the threshold of each. In other words, if the accelerometer…

### Feeding a neural network with single slices of a 3D matrix

I’m working on a neural network wich “slices” a 1080p image in many layers. It takes a 1080p image as an input and produces a 1080*1920*n matrix: basically I add a z value to each pixel rapresenting the layer that that pixel belongs to; the max z value is n. The next step would be…

### What are evolutionary algorithms for topology and weights evolving of ANN (TWEANN) other than NEAT?

I wonder if there are other than NEAT approaches to evolving architectures and weights of artificial neural networks? To be more specific I am looking for projects/frameworks/libraries that use evolutionary/genetic algorithms to simultanousely evolve both topology and train weights of ANNs other than NEAT approach.

### Porting from Python to Octave

I am trying to solve a problem in deep reinforcement learning. In order to better debug issues, I rendered a simplistic version of the environment in Python in order to be able to use the Pytorch framework. I am interested in seeing how this learned policy performs in the original environment. So I am looking…

### CNN for image-to-image mapping

I am working on a problem in which I need to train a neural network to map one or more input images to one or more output images (1 channel for image). Below I report some examples of input&output. In this case I report 1 input and 1 output image, but may need to pass…

### CNN for image-to-image mapping

I am working on a problem in which I need to train a neural network to map one or more input images to one or more output images (1 channel for image). Below I report some examples of input&output. In this case I report 1 input and 1 output image, but may need to pass…

### CNN for image-to-image mapping

I am working on a problem in which I need to train a neural network to map one or more input images to one or more output images (1 channel for image). Below I report some examples of input&output. In this case I report 1 input and 1 output image, but may need to pass…

### CNN positional based feature extraction

Not sure where to ask this as it’s a fairly advanced question but: A major problem with deep learning according to hinton is that operations like max-pooling remove the position information of features with respect to each other. I’m wondering, how one might attempt to track feature locations in a Deep net?

### Scoring feature vector with Support Vector Machine

I am reading the R-CNN paper by Ross Girshick1 et al. (link) and I fail to understand how they do the inference. This is described in the section 2.2.Test-time Detection in the paper. I quote: At test time, we run selective search on the test image to extract around 2000 region proposals (we use selective…