AIP-210 Questions and Answers

Text vectorization is a technique that converts text into numerical vectors that can be used by machine learning models. Text vectorization can use different methods to represent text features, such as word frequency, word order, word meaning, or word context. Some of the common text vectorization methods are:

• TF-IDF: TF-IDF (term frequency-inverse document frequency) is a method that assigns a weight to each word based on its frequency in a document and its rarity across a collection of documents. TF-IDF can capture the importance and relevance of words for a given topic or domain, but it does not consider the order or meaning of words.
• Word2vec: Word2vec is a method that learns a vector representation for each word based on its context in a large corpus of text. Word2vec can capture the semantic and syntactic similarity and relationships among words, as well as preserve the order of words.

For an English-to-Spanish translation machine, using Word2vec would be appropriate and correctly defined, because in translation machines, we need to consider the order of the words, as well as their meaning and context.

A neural network without an activation function is equivalent to a form of a linear regression. A neural network is a computational model that consists of layers of interconnected nodes (neurons) that process inputs and produce outputs. An activation function is a function that determines the output of a neuron based on its input. An activation function can introduce non-linearity into a neural network, which allows it to model complex and non-linear relationships between inputs and outputs. Without an activation function, a neural network becomes a linear combination of inputs and weights, which is essentially a linear regression model.

Random forest is an ensemble learning method that combines multiple decision trees to create a more accurate and robust classifier or regressor. Random forest can convey each feature’s relative contribution to the model’s accuracy by measuring how much the prediction error increases when a feature is randomly permuted. This metric is called feature importance or Gini importance. Random forest can also provide insights into the interactions and dependencies among features by visualizing the decision trees .

NLTK (Natural Language Toolkit) is a Python library that provides a set of tools and resources for natural language processing (NLP). NLP is a branch of AI that deals with analyzing, understanding, and generating natural language texts or speech. NLTK offers modules for various NLP tasks, such as tokenization, stemming, lemmatization, parsing, tagging, chunking, sentiment analysis, named entity recognition, machine translation, text summarization, and more .

An activation function is a function that determines the output of a neuron in a neural network based on its input. An activation function can introduce non-linearity into a neural network, which allows it to model complex and non-linear relationships between inputs and outputs. Some of the common activation functions are:

• Sigmoid: A sigmoid function is a function that maps any real value to a value between 0 and 1. It has an S-shaped curve and is often used for binary classification or probability estimation.
• Hyperbolic tangent: A hyperbolic tangent function is a function that maps any real value to a value between -1 and 1. It has a similar shape to the sigmoid function but is symmetric around the origin. It is often used for regression or classification problems.
• ReLU: A ReLU (rectified linear unit) function is a function that maps any negative value to 0 and any positive value to itself. It has a piecewise linear shape and is often used for hidden layers in deep neural networks.

Additive is not an activation function, but rather a term that describes a property of some functions. Additive functions are functions that satisfy the condition f(x+y) = f(x) + f(y) for any x and y. Additive functions are linear functions, which means they have a constant slope and do not introduce non-linearity.

 Transparency is an ethical principle that describes the degree to which an AI system can provide clear and understandable information about its inputs, outputs, processes, and decisions. Transparency can help increase trust and confidence among users and stakeholders, as well as enable accountability and responsibility for the system’s actions and outcomes. Logging and storing historical predictions for potential, future access requests is an example of transparency, as it can help provide evidence and explanation for the system’s recommendations, as well as facilitate auditing and feedback.

Entanglement in ML pipelines occurs when a change in one step affects other steps that depend on it. Changing the normalization function in the feature engineering step would affect the model training and evaluation steps, as they rely on the features generated by the feature engineering step. Therefore, this scenario is an example of entanglement in ML pipelines. The other scenarios are not examples of entanglement, as they do not affect other steps in the pipeline.

A handover is the process of transferring the ownership and responsibility of an ML system from one party to another, such as from the developers to the end users. A handover should include all the necessary information and resources that enable the end users to use and run a trained model on their own system. Some of the items that should be included in a handover are:

• Link to a GitHub repository of the codebase: A GitHub repository is an online platform that hosts the source code and version control of an ML system. A link to a GitHub repository can provide the end users with access to the latest and most updated version of the codebase, as well as the history and documentation of the changes made to the code.
• README document: A README document is a text file that provides an overview and instructions for an ML system. A README document can include information such as the purpose, features, requirements, installation, usage, testing, troubleshooting, and license of the system.
• Sample input and output data files: Sample input and output data files are data files that contain examples of valid inputs and expected outputs for an ML system. Sample input and output data files can help the end users understand how to use and run the system, as well as verify its functionality and performance.

Technical debt is a metaphor that describes the implied cost of additional work or rework caused by choosing an easy or quick solution over a better but more complex solution. Technical debt can accumulate in ML systems due to various factors, such as changing requirements, outdated code, poor documentation, or lack of testing. Some of the ways to decrease technical debt in ML systems are:

• Documentation readability: Documentation readability refers to how easy it is to understand and use the documentation of an ML system. Documentation readability can help reduce technical debt by providing clear and consistent information about the system’s design, functionality, performance, and maintenance. Documentation readability can also facilitate communication and collaboration among different stakeholders, such as developers, testers, users, and managers.
• Refactoring: Refactoring is the process of improving the structure and quality of code without changing its functionality. Refactoring can help reduce technical debt by eliminating code smells, such as duplication, complexity, or inconsistency. Refactoring can also enhance the readability, maintainability, and extensibility of code.

Unsupervised learning is a type of machine learning that involves finding patterns or structures in unlabeled data without any predefined outcome or feedback. Unsupervised learning can be used for various tasks, such as clustering, dimensionality reduction, anomaly detection, or association rule mining. Some of the common algorithms for unsupervised learning are:

• Principal components analysis: Principal components analysis (PCA) is a method that reduces the dimensionality of data by transforming it into a new set of orthogonal variables (principal components) that capture the maximum amount of variance in the data. PCA can help simplify and visualize high-dimensional data, as well as remove noise or redundancy from the data.
• K-means clustering: K-means clustering is a method that partitions data into k groups (clusters) based on their similarity or distance. K-means clustering can help discover natural or hidden groups in the data, as well as identify outliers or anomalies in the data.
• Apriori algorithm: Apriori algorithm is a method that finds frequent itemsets (sets of items that occur together frequently) and association rules (rules that describe how items are related or correlated) in transactional data. Apriori algorithm can help discover patterns or insights in the data, such as customer behavior, preferences, or recommendations.

The optimal value of K is the one that minimizes the inertia or within-cluster sum of squares, while avoiding too many clusters that may overfit the data. The elbow plot shows a sharp decrease in inertia from K = 1 to K = 2, and then a more gradual decrease from K = 2 to K = 3. After K = 3, the inertia does not change much as K increases. Therefore, the elbow point is at K = 3, which is the optimal value of K for this data. References: How to Run K-Means Clustering in Python, K-means clustering - Wikipedia

Semi-supervised learning is a type of machine learning that uses both labeled and unlabeled data to train a model. Semi-supervised learning can be useful when:

• Labeling data is challenging and expensive: Labeling data requires human intervention and domain expertise, which can be costly and time-consuming. Semi-supervised learning can leverage the large amount of unlabeled data that is easier and cheaper to obtain and use it to improve the model’s performance.
• There is a large amount of unlabeled data to be used for predictions: Unlabeled data can provide additional information and diversity to the model, which can help it learn more complex patterns and generalize better to new data. Semi-supervised learning can use various techniques, such as self-training, co-training, or generative models, to incorporate unlabeled data into the learning process.

Distributed artificial intelligence (DAI) is a subfield of artificial intelligence that studies how multiple intelligent agents can coordinate and cooperate to achieve a common goal or solve a complex problem. DAI relies on a distributed system that performs robust computations across a network of unreliable nodes, such as sensors, robots, or humans. DAI can handle large-scale, dynamic, and uncertain environments that are beyond the capabilities of a single agent. References: [Distributed artificial intelligence - Wikipedia], [Distributed Artificial Intelligence: An Overview]

Adversarial attacks are malicious attempts to fool or manipulate machine learning models by adding small perturbations to the input data that are imperceptible to humans but can cause significant changes in the model output. In general, models that perform their tasks more accurately are less robust against adversarial attacks, because they tend to have higher confidence in their predictions and are more sensitive to small changes in the input data. References: [Adversarial machine learning - Wikipedia], [Why Are Machine Learning Models Susceptible to Adversarial Attacks? | by Anirudh Jain | Towards Data Science]

Neural network models are suitable for classification problems with a large number of features, because they can learn complex and non-linear patterns from high-dimensional data. They can also handle image data, which is likely to be the input for the human face detection problem. Neural networks can also be trained using transfer learning, which can leverage pre-trained models on similar tasks and improve the accuracy and efficiency of the model. References: [Neural network - Wikipedia], [Transfer Learning - Machine Learning’s Next Frontier]

Underfitting is a problem that occurs when a model learns too little from the training data and fails to capture the underlying complexity or structure of the data. Underfitting can result from using insufficient or irrelevant features, a low complexity of the model, or a lack of training data. Underfitting can reduce the accuracy and generalization of the model, as it may produce oversimplified or inaccurate predictions. Some of the ways to fix underfitting are:

• Add features to training data: Adding more features or variables to the training data can help increase the information and diversity of the data, which can help the model learn more complex patterns and relationships.
• Increase the complexity of the model: Increasing the complexity of the model can help increase its expressive power and flexibility, which can help it fit better to the data. For example, adding more layers or nodes to a neural network can increase its complexity.
• Train the model for more epochs: Training the model for more epochs can help increase its learning ability and convergence, which can help it optimize its parameters and reduce its error.

Getting more training data will not work to fix underfitting, as it will not change the complexity or structure of the data or the model. Getting more training data may help with overfitting, which is when a model learns too much from the training data and fails to generalize well to new or unseen data.

A false negative is an error where a positive case (belonging to the target class) is incorrectly predicted as negative (not belonging to the target class). A false negative rate is the ratio of false negatives to all actual positive cases. A low false negative rate means that most of the positive cases are correctly identified by the classifier.

For a diagnostic tool that can diagnose a particular disease so that individuals with the disease can receive treatment, it is of primary importance that it has a low false negative rate. This is because false negatives can have serious consequences for patients who have the disease but do not receive treatment, such as increased risk of mortality or complications. A low false negative rate can ensure that most patients who have the disease are diagnosed correctly and receive timely treatment.

A type 1 error in statistical hypothesis testing is when the null hypothesis is true, but is rejected. This means that the test falsely concludes that there is a significant difference or effect when there is none. The probability of making a type 1 error is denoted by alpha, which is also known as the significance level of the test. A type 1 error can be reduced by choosing a smaller alpha value, but this may increase the chance of making a type 2 error, which is when the null hypothesis is false but fails to be rejected. References: [Type I and type II errors - Wikipedia], [Type I Error and Type II Error - Statistics How To]

Hyperparameter optimization is the process of finding the optimal values for hyperparameters that control the learning process of a given algorithm. Hyperparameters are parameters that are not learned by the algorithm but are set by the user before training. Hyperparameters can affect the performance and behavior of the algorithm, such as its speed, accuracy, complexity, or generalization. Hyperparameter optimization can help improve the efficiency and effectiveness of the algorithm by tuning its hyperparameters to achieve the best results.

Concept drift, also known as model drift, occurs when the task that the model was designed to perform changes over time. For example, imagine that a machine learning model was trained to detect spam emails based on the content of the email. If the types of spam emails that people receive change significantly, the model may no longer be able to accurately detect spam. References: Understanding Data Drift and Model Drift: Drift Detection in Python | DataCamp, Machine Learning Monitoring, Part 5: Why You Should Care About Data and Concept Drift

Semi-supervised learning is an approach that is best if a limited portion of your training data is labeled. Semi-supervised learning is a type of machine learning that uses both labeled and unlabeled data to train a model. Semi-supervised learning can leverage the large amount of unlabeled data that is easier and cheaper to obtain and use it to improve the model’s performance. Semi-supervised learning can use various techniques, such as self-training, co-training, or generative models, to incorporate unlabeled data into the learning process.

Highly interpretable models are models that can provide clear and intuitive explanations for their predictions, such as decision trees, linear regression, or logistic regression. Some of the statements that are true regarding highly interpretable models are:

• They are usually easier to explain to business stakeholders: Highly interpretable models can help communicate the logic and reasoning behind their predictions, which can increase trust and confidence among business stakeholders. For example, a decision tree can show how each feature contributes to a decision outcome, or a linear regression can show how each coefficient affects the dependent variable.
• They usually compromise on model accuracy for the sake of interpretability: Highly interpretable models may not be able to capture complex or non-linear patterns in the data, which can reduce their accuracy and generalization. For example, a decision tree may overfit or underfit the data if it is too deep or too shallow, or a linear regression may not be able to model curved relationships between variables.