Human-AI Interaction Design Guidelines

Human-AI Interaction Design Guidelines

INITIALLY
01 Make clear what the system can do.

Help the user understand what the AI system is capable of doing.

02 Make clear how well the system can do what it can do.

Help the user understand how often the AI system may make mistakes.

Machine Learning workflow

Machine Learning Workflow consists of 3 components

• Explore and process data
• Modeling
• Deployment

Error functions

• In most learning networks, error is calculated as the difference between the actual output and the predicted output.
• The error function is which tells us how far are we from the solution.
• The function that is used to compute this error is known as loss function.
• Different loss functions will give different errors for the same prediction and thus would have a considerable effort on the performance of the model.

Canny edge detector

The Canny edge detector is an edge detection operator that uses a multi-stage algorithm to detect a wide range of edges in images. It was developed by John F. Canny in 1986. Canny also produced a computational theory of edge detection explaining why the technique works.

Grayscale to RGB conversion

we will convert an color image into a grayscale image. There are two methods to convert it. Both has their own merits and demerits. The methods are:

• Average method
• Weighted method or luminosity method
• using skimage

Average method

Average method is the most simple one. You just have to take the average of three colors. Since its an RGB image, so it means that you have add r with g with b and then divide it by 3 to get your desired grayscale image.

Its done in this way.

Grayscale = (R + G + B / 3)

MNIST GAN

Here we have 2 neural networks GENERATOR and  DISCRIMINATOR

DISCRIMINATOR:

• Is a simple classifier that tries to classify the images as real from the training set or fake generated images.

Flattening in NLP

• Instead of representing this 4*4 matrix, we can construct a vector with 16 entries.
• First 4 entries correspond to the first row.similarly 2nd 3rd and 4th

Note:After converting our image to an vector they can be fed to an input layer on NLP.

MoviePy

MoviePy is a Python module for video editing, which can be used for basic operations (like cuts, concatenations, title insertions), video compositing (a.k.a. non-linear editing), video processing, or to create advanced effects. It can read and write the most common video formats, including GIF.

Here it is in action (run in an IPython Notebook):

Gaussian Blur operation

---

In Gaussian Blur operation, the image is convolved with a Gaussian filter instead of the box filter. The Gaussian filter is a low-pass filter that removes the high-frequency components are reduced.

You can perform this operation on an image using the Gaussianblur()method of the imgproc class. Following is the syntax of this method −

GaussianBlur(src, dst, ksize, sigmaX)

This method accepts the following parameters −

• src − A Mat object representing the source (input image) for this operation.
• dst − A Mat object representing the destination (output image) for this operation.
• ksize − A Size object representing the size of the kernel.
• sigmaX − A variable of the type double representing the Gaussian kernel standard deviation in X direction.

Softmax function

• A wonderful activation function that turns numbers aka logits into probabilities that sum to one. 
• Outputs a vector that represents the probability distributions of a list of potential outcomes
• Core element that is used in deep learning task

Companies know more about you

People concerned about privacy often try to be “careful” online. They stay off social media, or if they’re on it, they post cautiously.  By doing so, they think they are protecting their privacy.

But they are wrong. Because of technological advances and the sheer amount of data now available about billions of other people, discretion no longer suffices to protect your privacy. Computer algorithms and network analyses can now infer, with a sufficiently high degree of accuracy, a wide range of things about you that you may have never disclosed, including your moods, your political beliefs, your sexual orientation and your health.

There is no longer such a thing as individually “opting out” of our privacy-compromised world.

What is to be done? Designing phones and other devices to be more privacy-protected would be start, and government regulation of the collection and flow of data would help slow things down. But this is not the complete solution. We also need to start passing laws that directly regulate the use of computational inference: What will we allow to be inferred, and under what conditions, and subject to what kinds of accountability, disclosure, controls and penalties for misuse?

Until we have good answers to these questions, you can expect others to continue to know more and more about you — no matter how discreet you may have been.

One Hot Encoding

One hot encoding is a process by which categorical variables are converted into a form that could be provided to ML algorithms to do a better job in prediction.

CATEGORICAL DATA

Lets take a dataset of food names. In this dataset, if there was another food name it would have categorical value as 4.As the no of unique value increases, the categorical values increases.

Data dimensions

SCALARS

• They have 0 dimensions
• Ex a persons height would be a scalar

1      2.4      -0.3

Bag of words

• Way of representing text data when modeling text with machine learning algorithms.
• Is simple to understand and implement and has seen great success in problems such as language modeling and document classification.

The Problem with Text

A problem with modeling text is that it is messy, and techniques like machine learning algorithms prefer well defined fixed-length inputs and outputs.

Machine learning algorithms cannot work with raw text directly; the text must be converted into numbers. Specifically, vectors of numbers.

In language processing, the vectors x are derived from textual data, in order to reflect various linguistic properties of the text.

This is called feature extraction or feature encoding.

A popular and simple method of feature extraction with text data is called the bag-of-words model of text.

ERROR FUNCTION IN NN

• In most learning networks, error is calculated as the difference between the actual output and the predicted output.
• The error function is which tells us how far are we from the solution.
• The function that is used to compute this error is known as loss function.
• Different loss functions will give different errors for the same prediction and thus would have a considerable effort on the performance of the model.

EXAMPLE:
Imagine, we are standing on top of a mountain(mount Everest) and we want to descend.It is not that easy and it is cloudy and it is big and we cant see the big picture.We would look at all the possible directions where we can walk.

Industries to be revolutionized by artificial intelligence

Artificial intelligence (AI) and machine learning (ML) have a rapidly growing presence in today’s world, with applications ranging from heavy industry to education. From streamlining operations to informing better decision making, it has become clear that this technology has the potential to truly revolutionize how the everyday world works.

According to a panel of Forbes Technology Council members, here are 13 industries that will soon be revolutionized by AI.

1. Cybersecurity

The enterprise attack surface is massive. With its power to bring complex reasoning and self-learning in an automated fashion at massive scale, AI will be a game-changer in how we improve our cyber-resilience. - Gaurav Banga, Balbix

GAN

• They can make entirely new image that are realistic, even they never been seen before
• Most of the application for GANs have been images

STACKGAN 

• Takes a textual description of the bird and than generating a high resolution of a bird matching that description.
• These pictures have never been seen before. It is not running a image search on a database, infact GAN is drawing a probability distribution over all hypothetical images matching that description
• We can keep running the GAN to get more images.

Sage Maker Services

SERVICES PROVIDED BY SAGEMAKER

1) Provides jupyter notebook instance

• Used to explore and process data

2) API

•  This simplifies computationally difficult task like train and deploy machine learning model

Machine Learning Workflow

Machine Learning Workflow consists of 3 components

• Explore and process data
• Modeling
• Deployment

EXPLORE AND PROCESS DATA

This component consists of exploring and processing the data.

Retrieve

The first step is to retrieve the data, which includes test and train dataset. Lets take an example of housing dataset which contains csv files. We need to download the data from the source.