Artificial intelligence is used as a fair term to represent various machine learning developments.

"We must develop a comprehensive global shared view of how technology is affecting our lives and reshaping the economic and social environments." Emboldened by the challenge, Nazareen Ebrahim is ready to answer the call to take on and profit amid the Fourth Industrial Revolution. Ebrahim is a senior media, communications and technology practitioner with a background in media strategy; project management; content development; training and facilitation; and radio and television presenting and production. She leads the artificial intelligence research team at Socially Acceptable, of which she is the CEO and founder. The company produced a 12-part artificial intelligence series that aims to educate professionals and the general public on artificial intelligence.

Artificial intelligence has been talked about for years, but is it really close to taking over the world? Could you rely on it to manage your business? "Maybe you're using artificial intelligence without knowing that," said Iva Ignjatovic. "AI is pretty much everywhere. Even search engines predict the full search item."

In current data science or machine learning applications, huge datasets and sophisticated networks are usually involved. Thus, code efficiency becomes really important when it comes to handling the computational workload. As an example, in a classic Multi-layer Perceptron (aka Feedforward Neural Network), the network typically contains multiple linear layers. Let's say the input layer contains 64 neurons while the first hidden layer contains 128 hidden neurons. Then, in order to calculate the output of the hidden layer given an input, the straightforward way would be to use the np.dot method provided by the Numpy library: As we can see, this method takes 1.4 microseconds on average.

This machine learning algorithm is the easiest one to understand. Also used in statistics, linear regression combines two variables.

In this post we will cover end to end Advanced Python ( Part 1) that you should know. In Python, a decorator is any callable Python object that is used to modify a function or a class. It takes a function, adds some functionality, and returns it.

There are multiple stages to running machine learning algorithms as it involves a sequence of tasks including pre-processing, feature extraction, model fitting, performance and validation. Pipeline is nothing but a technique through which we create linear sequence of data preparation and modeling steps to automate machine learning workflows. An automated pipeline consists of components and how those components can work together to produce and update the machine learning model. In this post, we are going to create pipeline, find best scalar, estimators and see accuracy score of different machine learning algorithms. We will be using Mines Vs Rocks dataset from Kaggle.

In this post we will cover end to end Intermediate Python( Part 2) that you should know. In python, Lambda is used to create small anonymous functions using "lambda" keyword and can be used wherever function objects are needed.It can any number of arguments but only one expression

Hyperparameters are those tunable parameters which can directly affect how well a model trains and are set before the learning process begins. Examples of hyperparameters are — For your ML model, in…

Keras is a very powerful open source Python library which runs on top of top of other open source machine libraries like TensorFlow, Theano etc, used for developing and evaluating deep learning models and leverages various optimization techniques. There are many in-built layers in Keras like Conv2D, MaxPooling2D, Dense, Flatten etc for different use cases and applications. In this project we are going to create custom(Parametric ReLU) layer and use it in the NN model to solve a multi classification problem (We will be using MNIST dataset) . We will be using the popular MNIST dataset. We will load the data using utils and then visualize it.