It provides an enterprise’s employees with a way to contribute new ideas through a gamification induced platform with the use of virtual coins by posting ideas/solutions and investing in the same.
​
Database: mongoDB
Tools used: IntelliJ IDEA , PHP, CSS3, HTML5, Javascript
Based on E-Commerce G2C model the website incorporates payment mechanism, security mechanism, asynchronous requests, session management, catalog designing, CRM and web services helping customers to pay bills.
Performed the following:
-
-
​Zero initialization
-
Random initialization
-
-
Regularization
-
​L2 Regularization
-
Dropout
-
-
Gradient Checking
-
​1-dimensional gradient checking
-
N-dimensional gradient checking
-
-
Used non-linear units like ReLU to improve model
-
Built a deeper neural network (with more than 1 hidden layer)
-
Implemented an easy-to-use neural network class
-
Built a basic Recurrent Neural Network
Predicted the class of iris plant using K-nearest neighbors algorithm to get an accuracy of 97%
Language used: Python
-
Implemented a 2-class classification neural network with a single hidden layer
-
Used units with a non-linear activation function, such as tanh
-
Computed the cross-entropy loss
-
Implemented forward and backward propagation
-
Built the general architecture of a learning algorithm, including:
-
Initializing parameters
-
Calculating the cost function and its gradients
-
-
Gathered all three functions above into the main model function, in the right order.