Transfer Learning for Image Classification – Part1

One of the most useful and emerging applications in the ML domain nowadays is using the transfer learning technique; it provides high portability between different frameworks and platforms. Once you’ve trained a neural network, what you get is a set of trained hyperparameters’ values. For example, LeNet-5 has 60k parameter values, AlexNet has 60 million, and VGG- 16 has about 138 million […]

Continue Reading

Neural Network training in parallel, distributed Vs. gpu

Training a network using a distributed system This is useful when your network is large enough that the matrix multiplications involved in training become unwieldy on a traditional PC. This problem is particularly prevalent when you have harsh time constraints (e.g. online training). If your thinking about a distributed system because you want to fiddle […]

Continue Reading