One of the key differences between the learning mechanism of humans and Artificial Neural Networks (ANNs) is the ability of humans to learn one task at a time. ANNs, on the other hand, can only learn multiple tasks simultaneously. Any attempts at learning new tasks incrementally cause them to completely forget about previous tasks. This lack of ability to learn incrementally, called Catastrophic Forgetting, is considered a major hurdle in building a true AI system. In this paper, our goal is to isolate the truly effective existing ideas for incremental learning from those that only work under certain conditions. To this end, we first thoroughly analyze the current state of the art (iCaRL) method for incremental learning and demonstrate that the good performance of the system is not because of the reasons presented in the existing literature. We conclude that the success of iCaRL is primarily due to knowledge distillation and recognize a key limitation of knowledge distillation, i.e, it often leads to bias in classifiers. Finally, we propose a dynamic threshold moving algorithm that is able to successfully remove this bias. We demonstrate the effectiveness of our algorithm on CIFAR100 and MNIST datasets showing near-optimal results. Our implementation is available at : https://github.com/Khurramjaved96/ incremental-learning.

No abstract

A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the opposite-they are highly prone to forgetting and rarely trained to facilitate future learning. One reason for this poor behavior is that they learn from a representation that is not explicitly trained for these two goals. In this paper, we propose OML, an objective that directly minimizes catastrophic interference by learning representations that accelerate future learning and are robust to forgetting under online updates in continual learning. We show that it is possible to learn naturally sparse representations that are more effective for online updating. Moreover, our algorithm is complementary to existing continual learning strategies, such as MER and GEM. Finally, we demonstrate that a basic online updating strategy on representations learned by OML is competitive with rehearsal based methods for continual learning. 1 1 We release an implementation of our method at https://github.com/khurramjaved96/mrcl 33rd Conference on Neural Information Processing Systems (NeurIPS 2019),

No abstract

The IEEE 802.11 based wireless LAN (WLAN) is most widely used for the real time communication such as Voice over IP (VOIP) video conferencing and etc. As the wireless internet access is increasing day by day by the combination of different small regions which are served by one operator or one Access Terminal. So there is the problem of mobility that a Mobile Node (MN) may move from one network to other network, also there is the problem of connectivity. To maintain the connectivity of a established call between two different networks using mobility management we proposed an efficient algorithm which maintain the real time connection as well as preventing the data loss during transition. We experiment our proposed algorithm by using a redundant buffer which store the data in transition mode and vanish the alternate data bits when the connection is establish with the network. The alternate data bit is also send for the same time as the time taken by the redundant buffer to disappear the data. This process saves our data in the transition time.