Humans can see and visually sense the world around them by using their eyes and brains. Computer vision works on enabling computers to see and process images in the same way that human vision does. Several algorithms developed in the area of computer vision to recognize images. The goal of our work will be to create a model that will be able to identify and determine the handwritten digit from its image with better accuracy. We aim to complete this by using the concepts of Convolutional Neural Network and MNIST dataset. We will also show how MatConvNet can be used to implement our model with CPU training as well as less training time. Though the goal is to create a model which can recognize the digits, we can extend it for letters and then a person’s handwriting. Through this work, we aim to learn and practically apply the concepts of Convolutional Neural Networks.

In this paper, the intention has to create a network configuration that is similar for all routing protocols RIP, OSPF, and EIGRP by which we want to analysis the performance of these protocols using Cisco Packet Tracer and OPNET simulator. We use various protocols for forwarding the packets in a network topology. For successful delivery of the packets from the source node to the accurate destination node, the routers maintain a routing table. The amount of network information stored by a router depends on its algorithm. For the performance measure, we will simulate real-time scenarios of the networks using Cisco Packet Tracer and OPNET simulation tools. We will evaluate the performance of EIGRP, OSPF, and RIP based on of network convergence, Ethernet delay, security, and bandwidth requirement, etc. We will observe that the EIGRP routing protocol has the maximum link utilization followed by OSPF, and RIP routing protocols.