AI Project Cycle PDF

CHAPTER 2: AI PROJECT CYCLE 1. Name all the stages of an AI Project cycle. Problem Scoping, Data Acquisition, Data Exploration, Modeling, Evaluation 2. What are sustainable development goals? The Sustainable Development Goals (SDGs), also known as the Global Goals, were adopted by a...

CHAPTER 2: AI PROJECT CYCLE 1. Name all the stages of an AI Project cycle. Problem Scoping, Data Acquisition, Data Exploration, Modeling, Evaluation 2. What are sustainable development goals? The Sustainable Development Goals (SDGs), also known as the Global Goals, were adopted by all United Nations Member States in 2015 as a universal call to action to end poverty, protect the planet and ensure that all people enjoy peace and prosperity. 3. Name the 4Ws of problem canvases under the problem scoping stage of the AI Project Cycle. a. Who, b. what c. where d. why 4. What is Training dataset & Testing Dataset? 5. What are the two different approaches for AI modelling? Define them. There are two approaches for AI Modelling are  Rule Based  Learning Based.  Rule Based : In this approach, the rules are defined by the developer. The machine follows the rules or instructions mentioned by the developer and performs its task accordingly. 1  So, it‟s a static model. i.e. the machine once trained, does not take into consideration any changes made in the original training dataset. Thus, machine learning gets introduced as an extension to this as in that case, the machine adapts to change in data and rules and follows the updated path only, while a rule-based model does what it has been taught once.  Learning Based : It‟s a type of AI modelling where the machine learns by itself. Under the Learning Based approach, the AI model gets trained on the data fed to it and then is able to design a model which is adaptive to the change in data. That is, if the model is trained with X type of data and the machine designs the algorithm around it, the model would modify itself according to the changes which occur in the data so that all the exceptions are handled in this case. After training, the machine is now fed with testing data. Now, the testing data might not have similar images as the ones on which the model has been trained. So, the model adapts to the features on which it has been trained and accordingly predicts the output. In this way, the machine learns by itself by adapting to the new data which is flowing in. This is the machine learning approach which introduces the dynamicity in the model. 6. Explain the various classification of learning based approach with neat diagram.  Supervised Learning: In a supervised learning model, the dataset which is fed to the machine is labelled. In other words, we can say that the dataset is known to the person who is training the machine only then he/she is able to label the data. A label is some information which can be used as a tag for data. 2  For example, students get grades according to the marks they secure in examinations. These grades are labels which categorize the students according to their marks. There are two main types of supervised learning models: 1. Classification: It refers to the supervised learning algorithm. The classification Model works on the labelled data. For example, we have 3 coins of different denomination which are labelled according to their weight then the model would look for the labelled features for predicting the output. This model works on discrete dataset which means the data need not be continuous. 2. Regression: It refers to the supervised learning algorithm. These models work on continuous data to predict the output based on patterns. For example, if you wish to predict your next salary, then you would put in the data of your previous salary, any increments, etc., and would train the model. Here, the data which has been fed to the machine is continuous.  Unsupervised Learning An unsupervised learning model works on unlabeled dataset. This means that the data which is fed to the machine is random and there is a possibility that the person who is training the model does not have any information regarding it. The unsupervised learning models are used to identify relationships, patterns and trends out of the data which is fed into it. It helps the user in understanding what the data is about and what are the major features identified by the machine in it. For example, you have a random data of 1000 dog images and you wish to understand some pattern out of it, you would feed this data into the unsupervised learning model and would train the machine on it. After training, the machine would come up with patterns which it was able to identify out of it. The Machine might come up with patterns which are already known to the user like colour or it might even come up with something very unusual like the size of the dogs. 3  There are two main types of unsupervised learning models: 1. Clustering: It refers to the unsupervised learning algorithm which can cluster the unknown data according to the patterns or trends identified out of it. The patterns observed might be the ones which are known to the developer or it might even come up with some unique patterns out of it. 2. Dimensionality Reduction We humans are able to visualize up to 3-Dimensions only but according to a lot of theories and algorithms, there are various entities which exist beyond 3-Dimensions. For example, in Natural language Processing, the words are considered to be N- Dimensional entities. Which means that we cannot visualize them as they exist beyond our visualization ability. Hence, to make sense out of it, we need to reduce their dimensions. Here, dimensionality reduction algorithm is used.  Reinforcement Learning It a type of machine learning technique that enables an agent(model) to learn in an interactive environment by trial and error using feedback from its own actions and experiences. Though both supervised and reinforcement learning use mapping between input and output, unlike supervised learning where feedback provided to the agent(model) is correct set of actions for performing a task, reinforcement learning uses rewards and punishment as signals for positive and negative behavior. Reinforcement learning is all about making decisions sequentially. 7. Explain Data Exploration stage. In this stage of project cycle, we try to interpret some useful information out of the data we have acquired. For this purpose, we need to explore the data and try to put it uniformly for a better understanding. This stage deals with validating or verification of the collected data and to analyze that:  The data is according to the specifications decided.  The data is free from errors.  The data is meeting our needs. 4  8. What are the different types of sources of data from where we can collect reliable and authentic datasets? Explain in brief. Data can be a piece of information or facts and statistics collected together for reference or analysis. Whenever we want an AI project to be able to predict an output, we need to train it first using data There could be many ways and sources from where we can collect reliable and authentic datasets namely:  Surveys  Web scrapping(from website)  Sensors  Cameras  Observations  Research  Investigation  API  Internet 9. Explain the AI Project Cycle in detail. The steps involved in AI project cycle are as given:  Problem Scoping: The first step is Scope the Problem by which, we set the goal for our AI project by stating the problem which you wish to solve with it. Under problem scoping, we look at various parameters which affect the problem we wish to solve so that the picture becomes clearer  Data Acquisition: Used to acquire data which will become the base of the project as it will help us in understanding what the parameters that are related to problem scoping.  Data Exploration: Collect data from various reliable and authentic sources. Since the data we collected would be in large quantities, you can try to give it a visual image of different types of representations like graphs, databases, flow charts, maps, etc. This makes it easier for us to interpret the patterns in which we acquired data follows.  Data Modelling: After exploring the patterns, we can decide upon the type of model you would build to achieve the goal. For this, we can research online and select various models which give a suitable output. We can test the selected models and figure out which is the most efficient one. The most efficient model is now the base of your AI project and you can develop your algorithm around it. 5   Evaluation: Once the modelling is complete, now w e need to test t h e e f f i c i e n c y o f our model on some newly fetched data AI Model can be evaluated with four parameters 1. Acquisition, 2. Precision, 3. Recall & 4. F1 Score. 10. Explain 4Ws problem canvas. The 4Ws problem canvas is the basic template while scoping a problem and using this canvas, the picture becomes clearer while we are working to solve it. a) Who: The “Who” block helps you in analyzing the people getting affected directly or indirectly due to it? Under this, you find out who the „stakeholders‟ to this problem are and what you know about them. Stakeholders are the people who face this problem and would be benefitted with the solution. b) What: Under the “What” block, you need to look into what you have on hand. At this stage, you need to determine the nature of the problem. What is the problem and how do you know that it is a problem? c) Where: In this block, you need to focus on the context/situation/location of the problem. It will help you look into the situation in which the problem arises, the context of it, and the locations where it is prominent. d) Why: in the “Why” canvas, think about the benefits which the stakeholders would get from the solution and how would it benefit them as well as the society. 11. What are the features of an Artificial Neural Network? Any Artificial Neural Network, irrespective of the style and logic of implementation, has a few basic features as given below.  The Artificial Neural Network systems are modelled on the human brain and nervous system.  They are able to automatically extract features without feeding the input by programmer.  Every node of layer in a Neural Network is compulsorily a machine learning algorithm.  It is very useful to implement when solving problems for very huge datasets. 12. Differentiate between rule-based and learning-based AI modelling approaches.  Rule Based Approach: It refers to the AI modelling where the relationship or patterns in data are defined by the developer. The machine follows the rules or instructions mentioned by the developer, and performs its task accordingly. For example, suppose you have a dataset comprising of 100 images of apples and 100 images of bananas. To train your machine, you feed this data into the machine and label each image as either apple or banana. Now if you test the machine with the image of an apple, it will compare the image with the trained data and 6  according to the labels of trained images, it will identify the test image as an apple. This is known as Rule based approach. The rules given to the machine in this example are the labels given to the machine for each image in the training dataset.  Learning Based Approach: In this approach, the machine learns by itself. It refers to the AI modelling where the relationship or patterns in data are not defined by the developer. In this approach, random data is fed to the machine and it is left on the machine to figure out patterns and trends out of it. Generally, this approach is followed when the data is un labeled. For example, suppose you have a dataset of 1000 images of random stray dogs of your area. You would put this into a learning approach-based AI machine and the machine would come up with various patterns it has observed in the features of these 1000 images which you might not have even thought of! 13. What is an Artificial Neural Network? Explain the layers in an artificial neural network. Artificial Neural Network: Modeled in accordance with the human brain, a Neural Network was built to mimic the functionality of a human brain. The human brain is a neural network made up of multiple neurons, similarly, an Artificial Neural Network (ANN) is made up of multiple perceptrons. A neural network consists of three important layers: Input Layer: As the name suggests, this layer accepts all the inputs provided by the programmer. Hidden Layer: Between the input and the output layer is a set of layers known as Hidden layers. In this layer, computations are performed which result in the output. There can be any number of hidden layers Output Layer: The inputs go through a series of transformations via the hidden layer which finally results in the output that is delivered via this layer. 7 14. Explain the purpose of Problem Statement Template. The Problem Statement Template helps us to summarize all the key points into one single template. So that in the future, whenever there is a need to look back at the basis of the problem, we can take a look at the Problem Statement Template and understand its key elements of it. Have a look at Problem Statement Template. 15. Explain the importance of Evaluation in AI project cycle. Evaluation is a process of understanding the reliability of any AI model, based on outputs by feeding the test dataset into the model and comparing it with actual answers. i.e. oonce a model has been made and trained, it needs to go through proper testing so that one can calculate the efficiency and performance of the model. Hence, the model is tested with the help of Testing Data (which was separated out of the acquired dataset at Data Acquisition stage. The efficiency of the model is calculated on the basis of the parameters mentioned below: 1. Accuracy 2. Pression 3. Recall 4. F1 Score 8