Panda is open source, the BSD-licensed library used for data analysis in Python programming language. It is build on top of two most essential python packages numpy and matplotlib. If you have not installed panda please go through this link and play with the code. Data acquisition is the process of loading and reading data from various sources. To read any data from python panda package, we need to consider two important factor i.e. format…
A python library is a collection of functions and methods that allow you to perform lots of actions without writing any code. The libraries usually consist of built-in models providing different functionalities, which you can use directly. There are a lot of libraries offering a broad range of facilities. Below are some important python libraries used for data science. It is divided into three group i.e. Scientific Computing libraries, Visualization libraries, and Algorithmic libraries. Scientific…
The process of repeatedly nudging an input of a function by some multiple of the negative gradient is called gradient descent. It’s a way to converge towards some local minimum of a cost function basically valley in a graph. According to Wikipedia, Gradient descent is a first-order iterative optimization algorithm for finding the minimum of a function. To find a local minimum or minimum cost of a function using gradient descent, one takes steps proportional…
In Artificial Neural Network (ANN), the activation function of a neuron defines the output of that neuron given a set of inputs. For Neural Network to achieve maximum predictive power, we must apply activation function in the hidden layers. An activation function allows the model to capture non-linearities. Image 1 below from study.com gives examples of linear function and reduces nonlinear function. If the relationships in the data are not straight line relationships we will…
Have you ever thought of paying bills with your ATM card directly without any hassle? If you are a frequent visitor to online payment sites you might have had this idea several times. Now your dreams have come true with TULANAA, a product of Inspiring Lab Pvt Ltd. Tulanaa has got lots of features other than paying phone bills. Features like comparing packages of different telecom operators, optimizing phone bills, current offers from operators. Furthermore,…
Transfer Learning is a machine learning technique where model trained on one task could be applied to the different but related problem. For example (from Wikipedia), knowledge gained while learning to recognize cars could apply when trying to recognize trucks. This model is retrained in a similar problem which will drastically cut down the training time. To conduct deep learning could take days, but transfer learning helps to conduct the work in a very short…
This article is pretty short and to the point. If you are user of Anaconda you might have or would be encountered with this error. The possible issue that might cause this error is outdated navigator. Here the solution which solved my issue. It is well tested and Yes! it works. Open the terminal in your system. And follow the command below. $ conda update conda $ conda update anaconda-navigator $ conda update navigator-updater $…
Reinforcement learning is based on reinforcement theory in which a combination of reward and/or punishment is used to reinforce the wanted behavior or extinguish unwanted behavior. Software agents interact with the environment. In reinforcement learning agents can automatically figure out how to optimize their behavior given a system of rewards and punishment. It draws inspiration from behavioral psychology. It has applications in many fields. Such as: Economics Genetics Game Playing In 2016, reinforcement learning was…