User Portlet
| Discussions |
|---|
| Hello all. Is there support for "Change Streams" in MongoLink? https://www.mongodb.com/docs/manual/changeStreams/ I would like to monitor for changes in a MongoDB database within Mathematica. I am currently able to do so with CouchDB because it... |
| [@Mike Sollami][at0] Thank you for digging into this. In order to make Sabrina's code work again in v13, you can use the following definitions (before evaluating the layers/networks): ScalarTimesLayer[s_] := ElementwiseLayer[s*#&] ... |
| Given the Mac Pro and the latest powerful MacBook pros, etc. Wolfram should implement Metal support so that we can get GPU acceleration even on modern hardware without NVIDIA GPUs... Any words on this from Wolfram? They also advertise OpenCL... |
| Ugh... wish I would have read this before getting an RTX 2070. I there an ETA for Mma 12? Or a way to get this working before the release of 12? |
| And let me just say, the neural net repo is one of the most useful things I've seen in years. Well done. |
| 1. Yes, there is an example and the documentation does provide some assistance. But it's not complete enough. Look at NetTrain. It shows four potential forms of data. The example in the documentation for LossFunction covers Case 2. There's no... |
| That is correct. Note also: we should have some reinforcement learning examples in the upcoming 12 release documentation. We are busy adding a simple feature to the neural net framework that will allow you train agents using using the recently... |
| ![enter image description here][1] - Congratulations! This post is now a [Staff Pick][2] as distinguished by a badge on [your profile][3]! Thank you, keep it coming! [1]:... |
| Here's an example how to implement somewhat more complex like differential equations: *ODEs, SDEs, etc.* into **ElementwiseLayer[...]**: [DiffEq in Neural Net][1] (Open picture into new tab to see it in full size!) Depending on the result... |
| PNG is usually (always?) compressed. When its imported into the WL, the size increases (sometimes quite dramatically), as its stored as an uncompressed array in memory. This is one major advantage of out-of-core training: you can store all your... |