Most Popular
1500 questions
10
votes
1 answer
What is the difference between "expected return" and "expected reward" in the context of RL?
The value of a state $s$ under a certain policy $\pi$, $V^\pi(s)$, is defined as the "expected return" starting from state $s$. More precisely, it is defined as
$$
V^\pi(s) = \mathbb{E}\left(R_t \mid s_t = s \right)
$$
where $R_t$ can be defined…
user10640
10
votes
3 answers
Questions about LSTM cells, units and inputs
I'm trying to learn how LSTM networks work, and even if I get the basics, the details of the internal structure is not clear for me.
On this blog link, I found this scheme of a LSTM architecture
Where apparently, every circle should correspond to…
BBB
- 101
- 1
- 3
10
votes
1 answer
What is the name for this chart which splits a quantity by allocation to a class hierarchy?
I need to create this type of chart, where you can see a quantity is split into a hierarchy of classes or taxonomy. In the example below the quantity is a household monthly income, and the classes are different monthly expenditures, classified…
Ognyan
- 203
- 2
- 6
10
votes
3 answers
Log file analysis: extracting information part from value part
I'm trying to build a data set on several log files of one of our products.
The different log files have their own layout and own content; I successfully grouped them together, only one step remaining...
Indeed, the log "messages" are the best…
Michael Hooreman
- 793
- 2
- 9
- 21
10
votes
1 answer
What is the "novel reinforcement learning algorithm" in AlphaGo Zero?
For some reason, AlphaGo Zero isn't getting as much publicity as the original AlphaGo, despite its incredible results. Starting from scratch, it's already beaten AlphaGo Master and has passed numerous other benchmarks. Even more incredibly, it's…
Dubukay
- 203
- 1
- 7
10
votes
1 answer
A clear visualization of a two-way ANOVA
To provide a full yet simple picture of a 3-level, one-way ANOVA, I use the following visualization where variation within each group (the filled circles) and variation between the groups (black arrows) are simple to be understood.
But I'm wondering…
Reza Norouzian
- 101
- 2
10
votes
3 answers
Public dataset for news articles with their associated categories
I am wondering if there are any public datasets of Google news with various news categories such as politics, entertainment, lifestyle, general news, sports etc.
I want to use such dataset for topic detection of various sentences or paragraphs. I…
utengr
- 213
- 1
- 2
- 10
10
votes
1 answer
Cost function for Ordinal Regression using neural networks
What is the best cost function to train a neural network to perform ordinal regression, i.e. to predict a result whose value exists on an arbitrary scale where only the relative ordering between different values is significant (e.g: to predict…
xboard
- 368
- 3
- 14
10
votes
2 answers
How to get an aggregate confusion matrix from n different classifications
I want to test the accuracy of a methodology. I ran it ~400 times, and I got a different classification for each run. I also have the ground truth, i.e., the real classification to test against.
For each classification I computed a confusion matrix.…
gc5
- 879
- 2
- 9
- 17
10
votes
2 answers
Scalable Outlier/Anomaly Detection
I am trying to setup a big data infrastructure using Hadoop, Hive, Elastic Search (amongst others), and I would like to run some algorithms over certain datasets. I would like the algorithms themselves to be scalable, so this excludes using tools…
doublebyte
- 420
- 3
- 9
10
votes
2 answers
What is the difference between Pytorch's DataParallel and DistributedDataParallel?
I am going through this imagenet example.
And, in line 88, the module DistributedDataParallel is used. When I searched for the same in the docs, I haven’t found anything. However, I found the documentation for DataParallel.
So, would like to know…
Dawny33
- 8,296
- 12
- 48
- 104
10
votes
1 answer
How to use Embedding() with 3D tensor in Keras?
I have a list of stock price sequences with 20 timesteps each. That's a 2D array of shape (total_seq, 20). I can reshape it into (total_seq, 20, 1) for concatenation to other features.
I also have news title with 10 words for each timestep. So I…
offchan
- 305
- 3
- 10
10
votes
2 answers
Why does Q Learning diverge?
My Q-Learning algorithm's state values keep on diverging to infinity, which means my weights are diverging too. I use a neural network for my value-mapping.
I've tried:
Clipping the "reward + discount * maximum value of action" (max/min set to…
nedward
- 414
- 5
- 13
10
votes
4 answers
Why does it speed up gradient descent if the function is smooth?
I now read a book titled "Hands-on Machine Learning with Scikit-Learn and TensorFlow" and on the chapter 11, it has the following description on the explanation of ELU (Exponential ReLU).
Third, the function is smooth everywhere, including around z…
Blaszard
- 911
- 1
- 13
- 29
10
votes
1 answer
Can The linearly non-separable data be learned using polynomial features with logistic regression?
I know that Polynomial Logistic Regression can easily learn a typical data like the following image:
I was wondering whether the following two data also can be learned using Polynomial Logistic Regression or not.
I guess I have to add more…
Green Falcon
- 14,058
- 9
- 57
- 98