45 Matching Annotations
1. Aug 2019
2. en.wikipedia.org en.wikipedia.org
1. As log-bilinear regression model for unsupervised learning of word representations, it combines the features of two model families, namely the global matrix factorization and local context window methods

What does "log-bilinear regression" mean exactly?

#### URL

3. Jul 2019
4. en.wikipedia.org en.wikipedia.org
1. An Oblivious Tree is a rooted tree with the following property: All the leaves are in the same level. All the internal nodes have degree at most 3. Only the nodes along the rightmost path in the tree may have degree of one.

Note this is not the definition of the oblivious decision trees in the CatBoost paper.

There a oblivious decision tree means a tree where the feature used for splitting is the same across all intermediate nodes within the same level of the tree, and the leaves are all in the same level.

#### URL

5. Jun 2019
6. arxiv.org arxiv.org
1. features (sparse)

are these feature values or actual features?

2. Note that thescalar multipledoes not meanxkis linear withx0

x_k is not a linear function of x_0

3. We argue that the CrossNet learns a special typeof high-order feature interactions, where each hidden layer in theCrossNet is a scalar multiple ofx0

In that case CrossNet doesn't really learn anything?

4. multivalent,

takes on more than one value

5. univalent,

takes on a unique value

#### URL

7. Mar 2019
8. docs.python.org docs.python.org
1. heap.sort() maintains the heap invariant

may swap the indices of the nodes at the same height but will keep the sorted array a min heap

#### URL

9. medium.com medium.com
1. The most common error I see is a subconscious assumption that each word can have at most one synonym

Use sets as the value.

#### URL

10. Oct 2018
11. en.wikipedia.org en.wikipedia.org
1. The perplexity of the model q is defined as b − 1 N ∑ i = 1 N log b ⁡ q ( x i ) {\displaystyle b^{-{\frac {1}{N}}\sum _{i=1}^{N}\log _{b}q(x_{i})}}

The perplexity formula is missing the probability distribution $$p$$

#### URL

12. en.wikipedia.org en.wikipedia.org
1. It has been demonstrated that this formulation is almost equivalent to a SLIM model,[9] which is an item-item model based recommender

So a pre-trained item model can be used to make such recommendations.

2. The user's latent factors represent the preference of that user for the corresponding item's latent factors

The higher the value of the dot product between the two, the higher the preference.

3. two lower dimensional matrices

Not necessary (in fact, often not) square. Typically each user is represented by a vector of dimension strictly less than the number of items and vice versa.

#### URL

13. karpathy.github.io karpathy.github.io
1. are are

*are

#### URL

14. redis.io redis.io
1. it will not try to start a failover if the master link was disconnected for more than the specified amount of time

Why would it exhibit this behavior? Is it because a slave that's disconnected from the master for too long has stale data? Or is it because the slave made be failing as well?

1. 会话

Session

2. Python

#### URL

15. Sep 2018
16. docs.pymc.io docs.pymc.io
1. conditional distribution for individual components can be constructed

So the conditional distribution is conditioned on other components?

2. p(y∣x)=∫p(y∣f,x)p(f∣x)df

$$y$$ is the data, $$f$$ is the model, $$x$$ is the input variable

#### URL

17. am207.github.io am207.github.io
1. marginaly

*marginal

2. corvariance

*covariance

3. y=y1,…,yn=m

$$n = m$$

#### URL

18. am207.github.io am207.github.io
1. must store an amount of information which increases with the size of the data

Or you can use MCMC.

2. some

*sum

3. calculation once again involves inverting a NxN matrix as in the kernel space representation of regression

this is why we use MCMC or other distribution sampling technique instead

4. $f(x_)foratestvectorinputforatestvectorinput for a test vector input x_,givenatrainingsetXwithvaluesyfortheGPisonceagainagaussiangivenbyequationCwithameanvector,givenatrainingsetXwithvaluesyfortheGPisonceagainagaussiangivenbyequationCwithameanvector, given a training set X with values y for the GP is once again a gaussian given by equation C with a mean vector m_andcovariancematrixandcovariancematrix and covariance matrix k_$:

...$f(x)$ for a test vector input $x$, given a training set $X$ with values $y$ for the GP is once again a gaussian given by equation C with a mean vector $m$ and covariance matrix $k$:

5. corvariance

*covariance

6. in equation B for the marginal of a gaussian, only the covariance of the block of the matrix involving the unmarginalized dimensions matters! Thus “if you ask only for the properties of the function (you are fitting to the data) at a finite number of points, then inference in the Gaussian process will give you the same answer if you ignore the infinitely many other points, as if you would have taken them all into account!”(Rasmunnsen)

key insight into Gaussian processes

7. they

*the

8. im

*in

9. Notice now that the features only appear in the combination κ(x,x′)=xTΣx′,κ(x,x′)=xTΣx′,\kappa(x,x') = x^T \Sigma x', thus leading to writing the posterior predictive as p(f(x∗)|x∗,X,y)=N(κ(x∗,X)(κ(XT,X)+σ2I)−1y,κ(x∗,x∗)−κ(x∗,XT)(κ(XT,X)+σ2I)−1κ(XT,x∗))p(f(x∗)|x∗,X,y)=N(κ(x∗,X)(κ(XT,X)+σ2I)−1y,κ(x∗,x∗)−κ(x∗,XT)(κ(XT,X)+σ2I)−1κ(XT,x∗))p(f(x_*) | x_* , X, y) = N\left(\kappa(x_*,X) \left(\kappa(X^T,X) + \sigma^2 I\right)^{-1}y,\,\,\, \kappa(x_*,x_*) - \kappa(x_*,X^T)\left(\kappa(X^T,X) + \sigma^2 I\right)^{-1} \kappa(X^T,x_*) \right) The function κκ\kappa is called the kernel

#### URL

19. am207.github.io am207.github.io
1. generate

more like "sample"

2. f∗

$$f^*$$ denotes the model

#### URL

20. research.fb.com research.fb.com
1. Bayesian approach to handling observation noise

One core contribution of this work.

#### URL

21. mp.weixin.qq.com mp.weixin.qq.com
1. 通道剪枝算法

channel pruning algorithm

#### URL

22. Aug 2018
23. en.wikipedia.org en.wikipedia.org
1. expected values change during the series

So no longer identically distributed

#### URL

24. www.fast.ai www.fast.ai
1. To learn a network for Cifar-10, DARTS takes just 4 GPU days, compared to 1800 GPU days for NASNet and 3150 GPU days for AmoebaNet

What about in comparison to ENAS?

#### URL

25. Jul 2018
26. spark.apache.org spark.apache.org
1. partitioner

How to define a partitioner?

#### URL

27. mp.weixin.qq.com mp.weixin.qq.com
1. 极大极小(Max-min)博弈

Choose D to maximally discriminate D vs G and at the same time learn the real data; choose G to best "confuse" D.

2. 交叉熵

Cross entropy

3. 零和博弈

Zero-sum game

#### URL

28. Jun 2018
29. people.cs.bris.ac.uk people.cs.bris.ac.uk
1. isometrics in ROC space

What does this mean exactly?

#### URL

30. Local file Local file
1. you will have to do a lot of work to select appropriate input data and to code the data as numeric values

Not really anymore with the advent of convolutional neural networks.

#### Annotators

31. ai.intel.com ai.intel.com
1. next state s’

Is the next state s' the state reached by taking the action with the highest reward?

#### URL

32. May 2018
33. blog.cloudera.com blog.cloudera.com
1. The number of tasks is the single most important parameter.