在瑞典做硕士论文 (一) 导言 在Uppsala University 学习的第二年做硕士论文(Thesis)是大多数国际学生的选择。我从2020年10月开始找愿意接收我做Thesis的工业界机构，于当年12月中旬确定在Ericsson做Thesis student and Researcher. 大多数的国际硕士生都会选择在最后两个Periods做Thesis, 以期望能够在做Thesis的公司更容易地找到职位或者在教授那里拿到PhD的 offfer. November 19, 2020 15:40 Uppsal…
Natural Computation Methods for Machine Learning Note 15 In this article, we talk about Particle Swarm Optimization. In last post, we talked Computational tools, including Cellular automata Ant Colony Optimization Particle Swarm Optimization Particle Swarm Opt…
Natural Computation Methods for Machine Learning Note 14 Swarm Intelligence Intelligence <- Social behavior Intelligence can emerge from social interaction. Emergent behaviour – when a group behaves in ways that were not ”programmed” into its members Swarm …
Natural Computation Methods for Machine Learning Note 13 Properties of EC EC is parallel search (many balls in the landscape). Want to prevent all individuals from converging to the same solution (premature convergence – a common problem) The task of mutation …
Natural Computation Methods for Machine Learning Note 12 From course, I learned Evolutional Computing. Evolutionary computing (EC) population method Used for problems where the task is to maximize some measure of success Same family of problems as in RL, but v…
Natural Computation Methods for Machine Learning Note 11 Let us firstly revisit completive learning and SOFM Review CL and SOFM A node position (in the input space) is its weight vector, i.e. nodes move around in the same space as the data. Purpose of unsuperv…
Natural Computation Methods for Machine Learning Note 10 In this note, we are going talk about Deep Learning very briefly. Radial Basis Function Networks RBFNs are feedforward networks, where: The hidden nodes (the RBF nodes) compute distances, instead of weig…
Unsupervised Learning To learn from unlabeled data (only inputs, no target information). Most often for classification. Requires that class membership can be detected by structural properties (features) in the data, and that the learning system can be fund the…
Natural Computation Methods for Machine Learning Note 08 ex) Tic-Tac-Toe Assign value to each board position (state): +1 if the state is a winning terminal state. 0 if the state is a losing terminal state +0.5 to all other states (terminal and non–terminal) pl…
Natural Computation Methods for Machine Learning Note 07 From today, we are going to introduce reinforcement learning(RL). Forget ANNs for a while - RL is a field in its own right, independent from ANNs. However, as we will see, ANNs are sometimes used in RL. …
