-
How can we change the optimizer in Gluonts instead of stochastic gradient descent ? Suppose I want to use some evolutionary optimizer instead of SGD , how can I implement that in gluonts ??
-
Here I'm gonna kickstart first iteration of notebook for neural nets with numpy and scipy following:
- *instruction*, 30m: crash course in neural networks
+ along with live demo in Numpy
…
-
Hi,
Can you provide some information about the sgdr policy?
I suppose sgd stands for stochastic gradient descent? What does the "r" means?
I read somewhere that it's related to some cosine behaviou…
-
# BGD SGD MBGD
## Reference
- [随机梯度下降法，批量梯度下降法和小批量梯度下降法以及代码实现](https://blog.csdn.net/LoseInVain/article/details/78243051)
- [优化器（Optimizer）介绍](https://blog.csdn.net/weixin_41417982/article/de…
-
Gorgonia needs a website, I've been told. There are many features people don't know about, and they should be documented. Here's a rough framework in mind
* [ ] Basic Section
* [ ] Fundamental…
-
Hi and congrats on the package!
I'm one of the reviewers for the JOSS paper you submitted, so here I'll list my questions and concerns about the documentation. This issue will be updated as my read…
-
The [documentation of the property `losses`](https://www.tensorflow.org/probability/api_docs/python/tfp/layers/Convolution2DFlipout) of the class `Convolution2DFlipout` states
> Upon being built, t…
-
### Idea Title
Stochastic Gradient Descent (SGD)
### Idea Description
Stochastic Gradient Descent updates the model's parameters by calculating the gradient of the loss function for a single train…
-
Hi there!
In the 60-minute blitz tutorial (https://fluxml.ai/tutorials/2020/09/15/deep-learning-flux.html), the part where we train a network on CIFAR10 takes longer than expected. Could it be becaus…
-
# Non-gradient
- [x] Differential evolution: done #9
- [ ] DRAM: @ben18785 ? Very old PR #35
- [x] DREAM: done #10
- [x] Emcee hammer: done #12
- [x] Haario AC: done #6
- [x] Haario-Bardenet AC…