Günümüzde artan veri miktarıyla başa çıkabilmek için tek başına insan gücünün kullanılması mümkün görünmemektedir. Bu sebeple benzer dokümanları bir araya gruplayabilecek ya da dokümanları, önceden tanımlı kategorilere ...

A bi-criteria version of the curriculum-based university timetabling problem of ITC-2007 is solved using a multi-objective simulated annealing (MOSA) algorithm that identifies an approximation to the optimal Pareto front. ...

Traditional methods of generating timetables may not yield robust solutions that may easily be adapted to changing inputs. Incorporating late changes by making minimum modifications is an important need in many ...

For many combinatorial optimization problems, it is important to identify solutions that can be repaired without degrading solution quality in case changes in the data associated with the constraints make the initial ...

In this study, we consider the author verification problem as a binary classification problem where the aim is to identify whether the two inputs belong to the same author or not. For this task, we have used several ...

In this study, we propose a TripletMAML algorithm as an extension to Model-Agnostic Meta-Learning (MAML) which is the most widely-used optimization-based meta-learning algorithm. We approach MAML from a metric-learning ...