jabdakhata

An Artificial Neural Network, the primary constituent of Machine learning and Deep Learning, consists of the neurons, i.e. nodes grouped into Input Layer, Hidden Layer and the Output. The input layer provides the problem while the output layer classifies or finds the probability (like detecting the correct image or recognizing faces or texts). It is the hidden layer that is most interesting. The hidden layers are used in feature engineering to detect more and more features progressively as we move towards the output. This is done through  processes called forward propagation and back propagation. Simply put, the layers are connected to each other and provide input to each other and each input being associated with a suitable weight and accompanied by a bias. The weights are first chosen randomly and then the network is trained on a set of data. More the training data the better it is, as it may minimize the problem of overfitting esp. when there are too many features. The input signa

Artificial Intelligence is a term that is being widely used nowadays but as a concept it had captured human interest and imagination since last two centuries. Mary Shelley's Frankenstein was perhaps one of the early thoughts. Robots captured human imagination with limitless possibilities in the last century but the journey has been slow and tedious. Now Machine Learning and Deep Learning, the key ingredients of AI open up the frontiers to new opportunities. Machine Learning with Neural Networks based on Supervised and Unsupervised learning of data depend on a new paradigm called Data Science for training an algorithm with very large set of data so that the algorithm is able to predict results closer to the actual through minimization of errors. Neural Networks that are modeled after the interaction of neurons on human brains extend the possibility. Even though the AI concepts were theorized back in the 1950s and 1960s, the possibility of them concepts becoming practical could hav