**Active Learning**

Active learning is a special case of semi-supervised machine learning in which a learning algorithm is able to interactively query the user (or some other information source) to obtain the desired outputs at new data points. In statistics literature it is sometimes also called optimal experimental design. There are situations in which unlabeled data is abundant but manually labeling is expensive. In such a scenario, learning algorithms can actively query the user/teacher for labels. This type of iterative supervised learning is called active learning. … **Qualitative Data Science**

The often celebrated artificial intelligence of machine learning is impressive but does not come close to human intelligence and ability to understand the world. Many data scientists are working on automated text analysis to solve this issue (the topicmodels package is an example of such an attempt). These efforts are impressive but even the smartest text analysis algorithm is not able to derive meaning from text. To fully embrace all aspects of data science we need to be able to methodically undertake qualitative data analysis. … **Feed-Forward Neural Network Lattice Decoding Algorithm**

Neural network decoding algorithms are recently introduced by Nachmani et al. to decode high-density parity-check (HDPC) codes. In contrast with iterative decoding algorithms such as sum-product or min-sum algorithms in which the weight of each edge is set to $1$, in the neural network decoding algorithms, the weight of every edge depends on its impact in the transmitted codeword. In this paper, we provide a novel \emph{feed-forward neural network lattice decoding algorithm} suitable to decode lattices constructed based on Construction A, whose underlying codes have HDPC matrices. We first establish the concept of feed-forward neural network for HDPC codes and improve their decoding algorithms compared to Nachmani et al. We then apply our proposed decoder for a Construction A lattice with HDPC underlying code, for which the well-known iterative decoding algorithms show poor performances. The main advantage of our proposed algorithm is that instead of assigning and training weights for all edges, which turns out to be time-consuming especially for high-density parity-check matrices, we concentrate on edges which are present in most of $4$-cycles and removing them gives a girth-$6$ Tanner graph. This approach, by slight modifications using updated LLRs instead of initial ones, simultaneously accelerates the training process and improves the error performance of our proposed decoding algorithm. … **Siamese Deep Neural Network**

Siamese neural network is a class of neural network architectures that contain two or more identical subnetworks. identical here means they have the same configuration with the same parameters and weights. Parameter updating is mirrored across both subnetworks. Siamese NNs are popular among tasks that involve finding similarity or a relationship between two comparable things. Some examples are paraphrase scoring, where the inputs are two sentences and the output is a score of how similar they are; or signature verification, where figure out whether two signatures are from the same person. Generally, in such tasks, two identical subnetworks are used to process the two inputs, and another module will take their outputs and produce the final output. The picture below is from Bromley et al (1993). They proposed a Siamese architecture for the signature verification task. …

# If you did not already know

**23**
*Tuesday*
Mar 2021

Posted What is ...

in