Posts

I always encounter some ssh issue. Resource temporarily unavailable One day… > ssh -T git@github.com ssh: connect to host ssh.github.com port 22: Resource temporarily unavailable so there are several assumptions: windows firewall block port 22 I do not generate ssh key for my github account I do not configure my config file properly SSH dies I suggest following the steps below: restart ssh sudo service ssh restart reinstall ssh sudo apt-get remove openssh-server sudo apt-get install openssh-server generate ssh key for you github account generate ssh key...

GCN GCN originates from the article SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS. Suppose there is a undirected graph G(V,E) with vertices V and edges E. It has an adjacency matrix A(VxV). Each node has a feature and the feature matrix is X(VxN) We want to classify the nodes into M categories using neural network f(X,A). $$ f(X,A) = softmax(\hat{A} ReLU(\hat{A} XW(0))W(1)) $$ where $$ \hat{A} = D^{-\frac{1}{2}}AD^{-\frac{1}{2}} $$ It computes the symmetrically normalized adjacency matrix of G....

In face verification task, we have several metrics to measure model performances. Verification Rate (FR) under False Acceptance Rate First, we need to understand the false acceptance rate. There is a table showing reality and prediction. false acceptance rate is defined as “the percentage of identification instances, in which unauthorised cases are incorrectly accepted”. $$ FAR = \frac{FA}{FT} = \frac{False_Negative}{False_Negative+True_Negative} $$ Verification rate is the accuracy of a verification model....

Data analysis Warm up! We can use “describe” in psych package to see the number of participant, mean, std of a variable. library(psych) describe(penguins$body_mass_g) result vars n mean sd median trimmed mad min max range X1 1 342 4201.75 801.95 4050 4154.01 889.56 2700 6300 3600 skew kurtosis se X1 0.47 -0.74 43.36 What is TIDY DATA Every column is a variable Every row is an observation Every cell has one value It will benefit a lot if we deal with tidy data, for example, easy for data sharing, reproducible, easy to automate… Data cleaning Remove data hierachically!...

Harry Klopf’s Hedonistic Hypothesis Neurons will maximize the local analog of pleasure and minimize the local analog of pain, i.e. it is a RL agent. specific hypothesis When a neuron fires an action potential, all the contributing synapses become eligible to undergo changes in their efficacies, or weights. If the action potential is followed within an appropriate time period by an increase in reward, an efficacies of all eligible synapses increase (or decrease in the case of punishment)....