Read more… (7 words)
Read (7 words)
Machine Learning
8868 members.
For people getting started in machine learning, or interested in new research, news, and other discussions around it
CommonLounge is a community of learners who learn together. Get started with the featured resources above, ask questions and discuss related stuff with everyone.
NaN.
course
Learn Bioinformatics
Overview
This list consists of ~10 tutorials to learn bioinformatics. You can think of this list as a "Free Online Nano Book". We'll cover important bioinformatics topics, learning (a) the biological significance of each problem, and (b) the computational algorithms used to solve the problem. Everything is 100% free.
What is Bioinformatics?
Read more…(122 words)
Syllabus
Conserved Sequences and Regulatory Motifs with Brute-Force Algorithms and Randomized Algorithms
Conserver sequences and regulatory motifs are short sequences (say of length 15-30) which occur frequency in the genome. These sequences serve a variety of functions - such as regulating gene expression (and hence how much of a protein is produced) and indicating where genes begin. We'll see how to find these sequences using brute-force algorithms and randomized algorithms.
Genome Assembly and Sequence Alignment with Graph Algorithms and Dynamic Programming
Recently, we've figured out cost effective ways of sequencing a human genome, i.e. taking a human genome and reading sequence of 3-4 billion nucleic acids (A, C, G and T) that it comprises of. In this section, we'll see how this is achieved. We'll also see how we can find similar regions in two different genomes, which allows us to do things like infer evolutionary history and predict protein function.
Top comment in this discussion
Top comments in this discussion
NaN.
tutorial
Dropout (neural network regularization)
Dropout is a widely used regularization technique for neural networks. Neural networks, especially deep neural networks, are flexible machine learning algorithms and hence prone to overfitting. In this tutorial, we'll explain what is dropout and how it works, including a sample TensorFlow implementation.
If you [have] a deep neural net and it's not overfitting, you should probably be using a bigger one and using dropout, ... - Geoffrey Hinton [2]
Dropout algorithm
Dropout is a regularization technique where during each iteration of gradient descent, we drop a set of neurons selected at random. By drop, what we mean is that we essentially act as if they do not exist.
Read more…(528 words)
Top comments in this discussion
