#### Bias in Machine Learning

#### Machine Learning

Bias and variance are two major issues we try to manage in machine learning. We are always looking for a trade-off between the two. Bias has to do with the training data while variance has to do with the model output.

Bias in Machine Learning is defined as the phenomena of observing results that are systematically prejudiced due to faulty assumptions. ... This also results in bias which arises from the choice of training and test data and their representation of the true population.

#### Machine Learning with Python by Ajit Singh

#### Machine Learning

Machine learning can be described as a form of statistical analysis, often even utilizing well-known and familiar techniques, that has bit of a different focus than traditional analytical practice in applied disciplines. The key notion is that flexible, automatic approaches are used to detect patterns within the data, with a primary focus on making predictions on future data.

Python is a perfect choice for beginner to make your focus on in order to jump into the field of machine learning and data science.

#### What you are too afraid to ask about Artificial Intelligence Part II

#### Machine Learning

This article follows the first piece on machine learning describing how AI interacts with neuroscience, as well as how hardware and chips are getting created and modified to be more efficient for specific AI algorithm

Explanation about Neuroscience and AI and Hardware and AI are very nice. Thank you Francesco Corea for your wonderful article.

#### Students launch Machine Learning Society at Imperial

#### Machine Learning

Undergraduates Harry Berg (Mechanical Engineering) and Haron Shams (Design Engineering) have set up the Imperial College Machine Learning Society to get students involved in and inspired by technology that’s going to change the world.It is interesting that this society was planned by two undergraduate students and that the first event attracted 250 attendees, with over half of them being PhD students.

It is very nice initative by two undergraduate students Harry Berg (Mechanical Engineering) and Haron Shams (Design Engineering) .

#### Your First Machine Learning Project in Python Step-By-Step

#### Machine Learning

Do you want to do machine learning using Python, but you’re having trouble getting started?In this post, you will complete your first machine learning project using Python.In this step-by-step tutorial you will:Download and install Python SciPy and get the most useful package for machine learning in Python.Load a dataset and understand it’s structure using statistical summaries and data visualization.Create 6 machine learning models, pick the best and build confidence that the accuracy is reliable.If you are a machine learning beginner and looking to finally get started using Python, this tutorial was designed for you.https://machinelearningmastery.com/machine-learning-in-python-step-by-step/

Using A Structured Step-By-Step Process Any predictive modeling machine learning project can be broken down into 4 stages: 1.) Collect Data 2.) Pick the Model 3.) Train the Model 4.) Test the Model

#### Kaggle Learn

#### Machine Learning

Kaggle have just launched a set of free resources for learning Machine Learning, R, Data Visualisation and Deep Learning. They look like an ideal introduction for anyone wanting to get a start in these disciplines. Take a look here: https://www.kaggle.com/learn/overview

Kaggle allows users to find and publish data sets, explore and build models in a web-based data-science environment, work with other data scientists and machine learning engineers, and enter competitions to solve data science challenges.

#### Machine learning solves cognitive gear problem of a Recruiter

#### Machine Learning

Kate had been a busy recruiter and still she could not deliver her job pretty well. Business was not happy with her pace of recruitment and had been complaining that the delivery had slowed down due to the pace of recruitment. Kate had been working hard but world had moved ahead. Kate scans the resume and marks it for interview or selection. There are three issues in any job. A) Time to deliver. B) Context Switching and C) Complexity. Kate does a job of low complexity and high context switching. She has the time pressure to deliver. The solution to Kate problem looking at the changing context often from one resume to another resume looking at a large volume of data and concluding is going to come from a digital Assistant. So what is this Digital Assistant? A bot that can scan the resume find out quickly all the keywords and match the job descriptions , preferences of the hiring managers, get the social media handles and read thru them and gives a qualitative output is what Kate is looking as a solution. We may probably need a machine learning solution for Kate. Let us define Machine learning here. Machine learning is a program that acts on a class of Tasks T and gives a Performance P using the Experience E and this Performance P improves with the Experience E. Let us check what is the Task Kate had been doing? Kate had been classifying the resume and matching the job descriptions ie Task T. Her Performance P is the no of Resumes she is able to qualify a day with her Experience E. Machine Learning has two types of learnings namely Supervised Machine Learning and Unsupervised Machine Learning. Supervised Machine Learning is the one where you have given a label to learn. To give a simple example I teach machine the shape of Circle and if I give, any image that resembles Circle it is able to classify them as Circle. Similarly, if I need to teach the Machine about a resume and an output, which matches the job, description then I have to use a classifier algorithm. So a supervised machine learning classifies a given input in accordance with the output (label) it had been trained. So we have the input -> (Resume), Output (To be qualified for a specific job description). The first step is to train the machine by giving the input to a classifier algorithm and store the output as known to us. What is Training? You have a set of documents and say these documents belong to a certain topic. How you train and represent? The first step is to convert the document into a vector model. You have hundreds of resume and assume that each resume contains 1000 words you convert each resume into a vector model using TF-IDF algorithm. TF-IDF represents Term Frequency – Inverse Document Frequency a term often used in the information retrieval and text retrieval. Feed these documents into the algorithm and convert them into a vector model. The sentences as well as words in the document are stored in a vector model and you can store the same in the MongoDB. Each Vector Model represents a classified output say the job description. Say the Resume belongs to a Business Analyst. There is a word vector model for the sentences that qualify business analyst. The algorithm converted every resume into a vector and an output classification defining the job. Once you have a trained Engine for the resume reading and giving an accurate output then the next step is to input a new resume and based on the Experience E the classification will give a set of output as it had been trained. So what did the solution achieve? The performance P increased over a set of Tasks T with the experience E – So the Machine Learning made the life of people like Kate much easier.

8 problems that can be easily solved by Machine Learning Manual data entry. ... Detecting Spam. ... Product recommendation. ... Medical Diagnosis. ... Customer segmentation and Lifetime value prediction. ... Financial analysis. ... Predictive maintenance. ... Image recognition (Computer Vision)

#### Introduction to Artificial Neural Networks (ANNs)

#### Machine Learning

Introduction to Artificial Neural Networks (ANNs) White Paper 5 September 2017 Introduction Machine Learning (ML) is a subfield of computer science that stands behind the rapid development of Artificial Intelligence (AI) over the past decade. Machine Learning studies algorithms that allow machines recognizing patterns, construct prediction models, or generate images or videos through learning. ML algorithms can be implemented using a wide variety of methods like clustering, linear regression, decision trees, and more. In this paper, we are going to discuss the design of Artificial Neural Networks (ANN) – a ML architecture that gathered a powerful momentum in the recent years as one of the most efficient and fast learning methods to solve complex computer vision, speech recognition, NLP (Natural Language Processing), image, audio, and video generation problems. Thanks to their efficient multilayer design that models the biological structure of human brain, ANNs have firmly established themselves as the state-of-the-art technology that drives AI revolution. In what follows, we are going to describe the architecture of a simple ANN and offer you a useful intuition of how it may be used to solve complex nonlinear problems in an efficient way. What is an Artificial Neural Network? An Artificial Neural Network is an ML (Machine Learning) algorithm inspired by biological computational models of brain and biological neural networks. In a nutshell, an Artificial Neural Network (ANN) is a computational representation of the human neural network that regulates human intelligence, reasoning and memory. However, why should we necessary emulate a human brain system to develop efficient ML algorithms? The main rationale behind using ANNs (ANN) is that neural networks are efficient in complex computations and hierarchical representation of knowledge. Neurons connected by axons and dendrites into complex neural networks can pass and exchange information, store intermediary computation results, produce abstractions, and divide the learning process into multiple steps. Computation model of such system can thus produce very efficient learning processes similar to the biological ones. A perceptron algorithm invented in 1957 by Franc Rosenblatt in 1957 was the first attempt to create a computational model of a biological neural network. However, complex neural networks with multiple layers, nodes, and neurons became possible only recently and thanks to the dramatic increase of computing power (Moore’s Law), more efficient GPUs (Graphics Processing Units), and proliferation of Big Data used for training ML models. In the 2000s-2010s these developments gave rise to Deep Learning (DL), – a modern approach to the design of ANNs based on a deep cascade of multiple layers that extract features from data and do transformations and hierarchical representations of knowledge. Image #1 Overfitting problem Thanks to their ability to simulate complex nonlinear processes and create hierarchical, and abstract representations of data, ANNs stand behind recent breakthroughs in image recognition and computer vision, NLP (Natural Language Processing), generative models and various other ML applications that seek to retrieve complex patterns from data. Neural networks are especially useful for studying nonlinear hypotheses with many features (e.g n=100). Constructing an accurate hypothesis for such a large feature space would require using multiple high-order polynomials which would inevitably lead to overfitting – a scenario in which the model describes the random noise in data rather than underlying relationships and patterns. The problem of overfitting is especially tangible in image recognition problems where each pixel may represent a feature. For example, when working with 50 X 50 pixel images, we may have 25000 features which would make manual construction of the hypothesis almost impossible. A Simple Neural Network with a Single Neuron The simplest possible neural network consists of a single “neuron” (see the diagram below). Using a biological analogy, this ‘neuron’ is a computational unit that takes inputs via (dendrites) as electrical inputs (let’s say “spikes”) and transmits them via axons to the next layer or the network’s output. Image #2 A neural network with a single neuron In a simple neural network depicted above, dendrites are input features (x1, x2 …) and the outputs (axons) represent the results of our hypothesis (hw,b(x)). Besides input features, the input layer of a neural network normally has a 'bias unit' which is equal to 1. A bias unit is needed to use a constant term in the hypothesis function. In Machine Learning terms, the network depicted above has one input layer, one hidden layer (that consists of a single neuron) and one output layer. A learning process of this network is implemented in the following way. The input layer takes input features (e.g pixels) for each training sample and feeds them to the activation function that computes the hypothesis in the hidden layer. An activation function is normally a logistic regression used for classification, however, other alternatives are also possible. In the case described above, our single neuron corresponds exactly to the input-output mapping that was defined by logistic regression. Image #3 Logistic Regression As in the case with simple binary classification, our logistic regression has parameters. They are often called “weights” in the ANN (Artificial Neural Network) models. Multi-Layered Neural Network To understand how neural networks work, we need to formalize the model and describe it in a real-world scenario. In the image below we can see a multilayer network that consists of three layers and has several neurons. Here, as in a single-neuron network, we have one input layer with three inputs (x1,x2,x3) with an added bias unit (+1). The second layer of the network is a hidden layer consisting of three units/neurons represented by the activation functions. We call it a hidden layer because we don’t observe the values computed in it. Actually, a neural network can contain multiple hidden layers that pass complex functions and computations from the “surface” layers to the “bottom” of the neural network. The design of a neural network with many hidden layers is frequently used in Deep Learning (DL) – a popular approach in the ML research that gained a powerful momentum in recent years. Image #4 Multilayer Perceptron The hidden layer (Layer 2) above has three neurons (a12, a22, a32). In abstract terms, each unit/neuron of a hidden layer aij is an activation of unit/neuron in in the layer j. In our case, a unit a12 ctivates the first neuron of the second layer (hidden layer). By activation, we mean a value which is computed by the activation function (e.g logistic regression) in this layer and outputted by that node to the next layer. Finally, Layer 3 is an output layer that gets results from the hidden layer and applies them to its own activation function. This layer computes the final value of our hypothesis. Afterwards, the cycle continues until the neural network comes up with the model and weights that best predict the values of the training data. So far, we haven’t defined how the ‘weights’ work in the activation functions. For that reason, let’s define Q(j) as a matrix of parameters/weights that controls the function mapping from layer j to layer j + 1. For example, Q1 will control the mapping from the input layer to the hidden layer, whereas Q2 will control the mapping from the hidden layer to the output layer. The dimensionality of Q matrix will be defined by the following rule. If our network has sj units in the layer j and sj+1 units in the layer j+1, then Qj will have a dimension of sj+1 X (sj + 1). The + 1 dimension comes from the necessary addition in Qj of a bias unit x0 and Q0(j). In other words, our output nodes will not include the bias unit while the input nodes will. To illustrate how the dimensionality of the Q matrix works, let’s assume that we have two layers with 101 and 21 units in each. Then, using our rule Qj would be a 21 X 102 matrix with 21 rows and 102 columns. Image #5 A Neural Network Model Let’s put it all together. In the image above, we see our neural network with three layers again. What we need to do, is to calculate activation functions based on the input values, and our main hypothesis function based on the set of calculations from the previous layer (the hidden layer). In this case, our neural network works as a cascade of calculations where each subsequent layer supplies values to the activation functions of the next one. To calculate activations, we first have to define the dimensionality of our Q matrices. In this example, we have 3 input and 3 hidden units, so Q1 mapping from input to hidden layer is of dimension 3 X 4 because the bias unit is included. The activation layer of each hidden neuron (e.g a12) is equal to our sigmoid function applied to the linear combination of inputs with weights retrieved from the weight matrix Qj. In the diagram above, you can see that each activation unit is computed by the function g which is our logistic regression function. In its turn, Q2 refers to the matrix of weights that maps from the hidden layer to the output layer. These weights may be randomly assigned to the matrix before the neural network runs or be a product of previous computations. In our case, Q2 is a 1 X 4 dimensional matrix (i.e a row vector). To calculate the output results we apply our hypothesis function (sigmoid function) to the results calculated by the activation functions in the hidden layer. If we had several hidden layers, then the results of the previous activation functions would be passed to the next hidden layer and then to the output layer. This sequential mechanism makes neural networks very powerful in computation on nonlinear hypotheses and complex functions. Instead of trying to fit inputs to polynomial functions designed manually, we can create a neural network with numerous activation functions that exchange intermediary results and update weights. These automatic setup allows creating nonlinear models that are more accurate in prediction and classification of our data. Neural Networks in Action The power of neural networks to compute complex nonlinear functions may be illustrated using the following binary classification example taken from Coursera Machine Learning course by Professor Andrew Ngi. Consider the case when x1 and x2 can take two binary values (0,1). To put this binary classification problem in Boolean terms, our task is to compute y = x1 XOR x2 , which is the same as computing x1 XNOR x2. The latter is a logic gate that may be interpreted as NOT (x1 XOR x2). This is the same as saying that the function is true if both x1 and x2 are equal 0 or 1. To make our network calculate XNOR, we first have to describe simple logical functions to be used as intermediary activations in the hidden layer. The first function we want to compute is a logical AND function: y = x1 AND x2. Image #6 Logical AND function As in the first example above, our AND function is a simple single-neuron network with inputs x1 and x2 and a bias unit (+1). The first thing we need to do is to assign weights to the activation function and then compute it based on the input values specified in the truth table below. These input values are all possible binary values that x1 and x2 can take. By fitting 0s and 1s into the function (i.e logistic regression) we can compute our hypothesis. hq(x) = g(-30 + 20x1 + 20x2). To understand how the values of the third column of the truth table are found, remember that sigmoid function is 0 at ≈ -4.6 and 1 at ≈ 4.6. As a result, we have: x1 x2 hq(x) 0 0 g(-30) ≈ 0 0 1 g(-10) ≈ 0 1 0 g(-10) ≈ 0 1 1 g(10) ≈ 1 As we can see now, the rightmost column is a definition of a logical AND function that is true only if both x1 and x2 are true. The second function we need for our neural network to work is a logical OR function. In the logical OR, y is true (1) if either x1 OR x2 or both of them are 1 (true). Image #7 Logical OR function As in the previous case with the logical AND, we assign weights that will fit the definition of the logical OR function. Putting these weights into our logistic function g(-10 + 20x1 + 20x2) we get the following truth table: x1 x2 hq(x) 0 0 g(-10) ≈ 0 0 1 g(10) ≈ 1 1 0 g(-10) ≈ 1 1 1 g(10) ≈ 1 As you see, our function is false (0) only if both x1 and x2 are false. In all other cases, it is true. This corresponds to the logical OR function. The last function we need to compute before running a network for finding x1 XNOR x2 is (NOT x1) and (NOT x2). In essence, this function consists of two logical negations (NOT). A single negation NOT x1 may be presented in the following diagram. In essence, it says that y is true only if x1 is false. Therefore, the logical NOT has only one input unit (x1). Image #8 Logical NOT After putting inputs with weights into g = 10 – 20x1, we end up with the following truth table. x1 hq(x) 0 g(10) ≈ 1 1 g(-10) ≈ 0 The output values of this table confirm our hypothesis that NOT function outputs true only if x1 is false. Now, we can find out values of the logical (NOT x1) AND (NOT x2) function. Image #9 Logical (NOT x1) AND (NOT x2) Putting binary values of x1 and x2 in the function g(10 - 20x1 -20x2) we end up with the following truth table. x1 x2 hq(x) 0 0 g(10) ≈ 1 0 1 g(-10) ≈ 0 1 0 g(-10) ≈ 0 1 1 g(-30) ≈ 0 This table demonstrates that the logical (NOT x1) AND (NOT x2) function is true only if both x1 and x2 are false. These three simple functions (logical AND, logical OR, and double negation AND function) may be now used as the activation functions in our three-layer neural network to compute another nonlinear function defined in the beginning: x1 XNOR x2. To do this, we need to put these three simple functions together into a single network. Logical AND Logical (NOT x1) AND (NOT x2) Logical OR This network uses three logical functions calculated above as the activation functions. Image #10 A Neural Network to Compute XNOR Function As you see, the first layer of this network consists of two inputs (x1 and x2) plus a bias unit +1. The first unit of the hidden layer is a Logical AND activation function that takes weights specified above (-30, 20, 20). The second unit a(2)2 is represented by the (NOT x1) AND (NOT x2) function that takes parameters 10, -20, -20. Doing our usual calculations, we get the values 0,0,0,1 for a(2)1 and the values 1,0,0,0 for the second unit in the hidden layer. Now, the final step is using the second set of parameters from the logical OR function that sits in the output layer. What we do here, is simply take the values produced by the two units in the hidden layer (logical AND and (NOT x1) AND (NOT x2) ) and apply them to the OR function with its parameters. The results of this computation make up our hypothesis function (1,0,0,1), which is our desired XNOR function. x1 x2 a(2)1 a(2)2 hq(x) 0 0 0 1 1 0 1 0 0 0 1 0 0 0 0 1 1 1 0 1 That’s it! Hopefully, as this example illustrates, neural networks are powerful in computing complex nonlinear hypotheses by using a cascade of functions. In fact, neural networks can use output values of a certain function as the inputs of other functions. Leveraging this functionality, complex multi-layered networks that can extract complex features and patterns from images, videos, and other data can be designed. Conclusion Artificial Neural Networks (ANNs) are the main drivers of the contemporary AI revolution. Inspired by the biological structure of human brain, ANNs are powerful in modeling functions and hypotheses which would be hard to derive intuitively or logically. Instead of inventing your own function with high-order polynomials, which may lead to overfitting, one can design an efficient ANN architecture that can automatically fit complex nonlinear hypotheses to data. This advantage of the ANNs has been leveraged in the algorithmic feature extraction in computer vision and image recognition. For example, instead of manually specifying a finite list of image features to choose from, we can design a Convolutional Neural Network (CNN) that uses the same principle as the animal’s visual cortex to extract features. As a human eye, layers of the CNN respond to stimuli only in a restricted region of the visual field. This allows the network to recognize low-level features such as points, edges, or corners and gradually merge them into high-level geometric figures and objects. This example illustrates how good ANNs are in the automatic derivation of hypotheses and models from complex data that includes numerous associations and relationships.

Artificial Neural Networks or ANN is an information processing paradigm that is inspired by the way the biological nervous system such as brain process information. It is composed of large number of highly interconnected processing elements(neurons) working in unison to solve a specific problem.

#### Machine Learning Stanford University

#### Machine Learning

About this course: Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you'll learn about some of Silicon Valley's best practices in innovation as it pertains to machine learning and AI. https://www.coursera.org/learn/machine-learning

Both, Coursera vs Udemy, are effective for learning and offer a wide variety of different courses. Udemy is better for someone with a more relaxed learning style that wants to go through the course at their own pace. While Coursera is more of a traditional course format and timeline.

#### ANALYTICS How to Spot a Machine Learning Opportunity, Even If You Aren’t a Data Scientist

#### Machine Learning

Artificial intelligence is no longer just a niche subfield of computer science. Tech giants have been using AI for years: Machine learning algorithms power Amazon product recommendations, Google Maps, and the content that Facebook, Instagram, and Twitter display in social media feeds. But William Gibson’s adage applies well to AI adoption: The future is already here, it’s just not evenly distributed.https://hbr.org/2017/10/how-to-spot-a-machine-learning-opportunity-even-if-you-arent-a-data-scientist

Machine learning scientists can't work in a vacuum; business stakeholders should help them identify problems worth solving and allocate subject matter experts to distill their knowledge into labels for data sets, provide feedback on output, and set the objectives for algorithmic success.