All Questions
Tagged with mathematica machine-learning
6 questions
2
votes
0
answers
108
views
Maximum Uncertainty in Normal Distribution
While reading Goodfellow's Deep Learning Book, I came across the below fact about Normal Distribution. I am not sure I have understood what led to this conclusion, Can someone help with it?
"Out ...
- 51
0
votes
0
answers
483
views
How can Hinge loss be upper bound of the 0-1 loss?
I just have a question and I did not find clear explanation, hinge loss is upper bound of 0-1 loss, so does this mean upper bound regard to a single point loss such as 0 or 1 ?!. So, for example the 0-...
- 109
1
vote
1
answer
2k
views
How do we update the parameters (weights) in recurrent neural networks?
In RNNs, how do we update the weights?
I have following understanding of RNNs:
Parameters are shared across all time-steps, i.e.,
$$S_t = \tanh(U X_t + W S_{t-1} )$$
$$Y_k = \text{softmax}(V S_t)$$
...
- 31
1
vote
1
answer
107
views
How to simplify the understanding behind Hypothesis Testing? [duplicate]
Quote recently, I have trying to understand this confusing idea of Hypothesis testing. Although I am pretty much clear with the way it works, that is:
Choosing a test statistic
Then choosing a Null ...
- 11
0
votes
1
answer
435
views
How to derive the gradient for SSE cost function in Adaline?
I started learning machine learning and have some troubles in understanding derive rules for the gradient of cost function in particular I can't understand how sum(wjxj) transformed to -xj. I tried to ...
- 103
0
votes
1
answer
95
views
$X_1, X_2$ are IID $N(0,1)$. Find Cov($X_1$, $X_1 X_2$).
Two variables $X_1, X_2$ are independent and identically distributed as $N(0,1)$. I need to find
Cov($X_1$, $X_1 X_2$).
Thanks!
