Download Machine Learning Fundamentals and more Exams Nursing in PDF only on Docsity!
Introduction to Machine Learning
correct!!
What is ML? - ANS>A data science technique that extracts patterns from data to forecast future outcomes, behaviors and trends What are some applications of ML? - ANS>Natural language processing, Computer vision, analytics, decision making What is AI (artificial intelligence)? - ANS>a broad term that refers to computers thinking like humans What is ML (Machine learning?) - ANS>subcategory of AI that involves learning from data without being explicitly programmed What is DL (Deep Learning)? - ANS>subcategory of machine learning that uses a layered neural network architecture inspired by the human brain What are the steps of the data science process? - ANS>Collect data, prepare data, train model, evaluate model, deploy model, retrain model
What types of data does ML deal with? - ANS>Numerical, time-Series, Categorical, Text, Image What are some hallmarks of tabular data? - ANS>It is arranged in a data table with rows and columns What do the rows in tabular data represent? - ANS>single items (entities) What do the columns in tabular data represent? - ANS>properties of items What is the importance of vectors in ML? - ANS>It is used heavily to represent many things. Non-numerical data types are often converted into representative numerical vectors What are the two main approaches of scaling data? - ANS>Standardization and Normalization What is standardization? - ANS>a method of scaling data to have mean = 1 and std. deviation = 1 What is normalization? - ANS>A method of scaling data into the range [0,1]
How is image data represented? - ANS>Image data is represented by pixels What is depth in terms of image data? - ANS>Depth is how many channels the data has. RBG has depth of 3 and grayscale has depth 1 How is image data vectorized? - ANS>Each pixel is represented by [xpos, ypos, color]. 3-D vector size is [height][width][channel depth] so a 4x4 color image has vector size [4][4][3]. When it comes to image preprocessing, what are some of the transformations used? - ANS>Rotation, cropping, resizing, denoising, centering, normalizing, making the aspect ratio uniform How do you make image data have uniform aspect ratio? - ANS>make sure it's a square matrix How do you normalize image data? - ANS>mean pixel value in a channel from each pixel value in that channel How do you normalize text data? - ANS>transform it into canonical form. multiple spellings are reduced into single spelling (colour becomes color), different forms are reduced to a single form ('is, am, are' all becomes 'be')
What is lemmatization when it comes to text data? - ANS>reduces multiple inflections to a single dictionary form What are stop words? - ANS>high freq. words that are unwanted during text analysis What does it man to tokenize a string? - ANS>either split each strong of text into a list of smaller parts or tokens or split a sentence into separate keywords How do you vectorize text data? - ANS>Identify the particular features of the text that is relevant to the task Get features extracted in a numerical form that is accessible to ML algorithm via TF-IDF or word embedding What is TF-IDF and how does it work? - ANS>term frequency-inverse document frequency and it assigns less importance to common words or words that contain less information How does feature extraction for text data work? - ANS>Vectors can be visualized on a graph, the distance between two vectors is used to assess similarity in meaning or some connection.
[Notebooks, automated ML, designer, datasets, experiments, models, endpoints, compute, datastores] - ANS>Notebooks - Sample notebooks and user files loaded inside of compute instances Automated ML - Can automate intensive tasks that rapidly iterate over many combinations of algorithms, hyperparameters to find the best model based on the chosen metric
- Create new runs and view previous runs in the Automated ML tab Designer - Drag-and-drop tool that lets you create ML models without any code
- Has templates and can view drafts Datasets - Create datasets from local files, datastores, etc Experiments - Helps organize runs
- All runs must be associated with an experiment, can view all runs related to an experiment Models - Models are produced by runs in Azure ML, all models created in Azure or trained outside of Azure are accessible here
Endpoints - Exposes real-time endpoints for scoring or pipelines for advanced automation Compute - Designated compute resource where you run training script or host service deployment
- Manage compute instance, training cluster, inference cluster, attached compute Datastores - Attached storage account in which you can store datasets What is the difference between a model and an algorithm? - ANS>models are specific representations learned from data, algorithms are the processes of learning Model = Algorithm(data) What is a linear regression model? - ANS>It predicts a variable y from input variable x and assumes a simple linear relationship What are the forms for simple and multiple linear regressions? - ANS>Simple: Y = B0 + B1X Multiple: Y = B0 + B1X1 +B2X2 ... +BnXn
What is the difference between irreducible error and model error? - ANS>Model error is how different the predictions are from the actual output, can be reduced by refining the model learning process What is a parametric function? - ANS>parametric functions simplify mapping to a known functional form, general form is known, computes for coefficients and constants What is a non-parametric function? - ANS>no assumptions are made regarding the form of mapping between input and output data, free- form relationship formation between data, can have any functional form What are the benefits and limitations of parametric functions? - ANS>Benefits: simpler, easier to understand and interpret, faster learning from data, less training data required to learn mapping function Limitations: highly constrained to specific form of the function, limited complexity, poor fit in practice, not everything fits the underlying mapping function What are the benefits and limitations of non-parametric functions? - ANS>Benefits: highly flexible, can fit a large # of functional forms, makes
no assumptions on underlying function, high performance in prediction models produced Limitations: more training data needed, slower to train, generally has many parameters, risks overfitting the training data What are some properties of classical ML? - ANS>- based on classical mathematical algorithms
- more suitable for small data
- easier to interpret outcomes
- cheaper to perform
- can run on low-end machines
- doesn't require large amounts of computational power
- difficult to learn large datasets
- requires feature engineering
- difficult to learn complex features What are some properties of deep learning? - ANS>- based on neural networks
- suitable for high complexity problems
- better accuracy than classical ML
- better support for big data
What is reinforcement learning and what approaches does it entail? - ANS>Learns how an agent should take action in an environment to maximize a reward function Markov Decision Process active process where the actions of the agent influence the data observed in the future, hence influencing its own potential future states What distinguishes Classification algorithms? - ANS>outputs are categorical What distinguishes Regression algorithms? - ANS>outputs are numericaland continuous What distinguishes Clustering algorithms? - ANS>find inherent groups or clusters in the data, assigns entities to each cluster/group What are feature learning algorithms? - ANS>features are discovered or learned from the data What is anomaly detection? - ANS>algorithms used to detect abnormal data in a set of normal data
What is Bias? - ANS>simplifying assumptions made by a model that make the target function easier to learn Why is high bias bad? - ANS>Bias measures how inaccurate a model prediction is in comparison to true output so more bias = less accurate High bias = more assumptions + potentially miss important relationships b/t features and output, can cause underfitting What is Variance? - ANS>amount the estimate of the target function will change if different training data is used Why is high variance bad? - ANS>High variance suggests that the algorithm learns the random noise instead of the output and causes overfitting What is the tradeoff between bias and variance? - ANS>inverse relationship, models that are very complex usually have low bias and high variance Low complexity models usually have low variance and high bias
Reduce Dimensionality Stop training early when performance stops improving What is K-fold cross-validation? - ANS>Splits initial training data into k subsets and trains the model k times Used to reduce overfitting What is the Markov Decision Process? - ANS>Mathematical process to model decision making in situations where out comes are partly random and partly under the control of a decision maker Used in reinforcement learning
