Recent Comments
Category Archives: machine learning
A convolutional network to deconvolve calcium traces, living in an embedding space of statistical properties
As mentioned before (here and here), the spikefinder competition was set up earlier this year to compare algorithms that infer spiking probabilities from calcium imaging data. Together with Stephan Gerhard, a PostDoc in our lab, I submitted an algorithm based on convolutional networks. Looking … Continue reading
Spike detection competition
The main drawback of functional calcium imaging is its slow dynamics. This is not only due to limited frame rates, but also due to calcium dynamics, which are a slow transient readout of fast spiking activity. A perfect algorithm would infer the … Continue reading
Posted in Calcium Imaging, Data analysis, machine learning
Tagged Data analysis, machine learning, Matlab
2 Comments
Deep learning, part IV (2): Compressing the dynamic range in raw audio signals
In a recent blog post about deep learning based on raw audio waveforms, I showed what effect a naive linear dynamic range compression from 16 bit (65536 possible values) to 8 bit (256 possible values) has on audio quality: Overall perceived quality … Continue reading
Deep learning, part IV: Deep dreams of music, based on dilated causal convolutions
As many neuroscientists, I’m also interested in artificial neural networks and am curious about deep learning networks. I want to dedicate some blog posts to this topic, in order to 1) approach deep learning from the stupid neuroscientist’s perspective and 2) to get a feeling … Continue reading
Posted in machine learning
Tagged deep learning, machine learning, recurrent networks, theoretical neuroscience
8 Comments
Deep learning, part III: understanding the black box
As many neuroscientists, I’m also interested in artificial neural networks and am curious about deep learning networks. I want to dedicate some blog posts to this topic, in order to 1) approach deep learning from the stupid neuroscientist’s perspective and 2) to get a feeling … Continue reading
Deep learning, part II : frameworks & software
As many neuroscientists, I’m also interested in artificial neural networks and am curious about deep learning networks. I want to dedicate some blog posts to this topic, in order to 1) approach deep learning from the stupid neuroscientist’s perspective and 2) to get a feeling … Continue reading
Deep learning, part I
As many neuroscientists, I’m also interested in artificial neural networks and am curious about deep learning networks, which have gained a lot of public attention in the last couple of years. I’m not very familiar with machine learning, but I want to dedicate some blog … Continue reading