Less formal than a class lecture, a seminar allows for small groups to meet and discuss academic topics or required reading, as well as set goals for research and continuing investigation.<\/p>\n
The following seminar was conducted on Thursday 09-12-2021 at 3:00 PM by Dr. Abubakar M. Ashir, a Lecturer at the computer engineering department.<\/p>\n
seminar abstract:<\/p>\n
Transfer learning, used in machine learning, is the reuse of a pre-trained model on a new problem. In transfer learning, a machine exploits the knowledge gained from a previous task to improve generalization about another. For example, in training a classifier to predict whether an image contains food, you could use the knowledge it gained during training to recognize drinks<\/p>\n
In transfer learning, the knowledge of an already trained machine learning model is applied to a different but related problem. With transfer learning, we basically try to exploit what has been learned in one task to improve generalization in another. We transfer the weights that a network has learned at \u201ctask A\u201d to a new \u201ctask B.\u201d<\/p>\n
The general idea is to use the knowledge a model has learned from a task with a lot of available labeled training data in a new task that doesn’t have much data. Instead of starting the learning process from scratch, we start with patterns learned from solving a related task. Transfer learning is mostly used in computer vision and natural language processing tasks like sentiment analysis due to the huge amount of computational power required.<\/p>\n
Transfer learning isn\u2019t really a machine learning technique but can be seen as a \u201cdesign methodology\u201d within the field, for example, active learning. It is also not an exclusive part or study-area of machine learning. Nevertheless, it has become quite popular in combination with neural networks that require huge amounts of data and computational power.<\/p>\n","protected":false},"excerpt":{"rendered":"