Blockchain & Machine Learning Exam Notes

These flashcards cover key concepts and definitions related to blockchain, Bitcoin, and machine learning based on exam notes.

What does UTXO stand for in the context of Bitcoin?

Unspent Transaction Outputs.

What is mining in the blockchain context?

The process where miners take unconfirmed transactions from the mempool, form a block, and solve a Proof-of-Work (PoW) puzzle to add it to the blockchain.

What is the average time to mine a Bitcoin block?

10 minutes.

What is the maximum supply of Bitcoin?

21 million BTC.

How does Bitcoin determine consensus?

By accepting the longest valid chain.

What type of system does Bitcoin operate on?

Permissionless system where anyone can join.

What is the current reward for mining a block as per the notes?

3.125 BTC.

What is the mempool?

A temporary storage area where unconfirmed transactions wait before being included in a block.

What is overfitting in machine learning?

When a model learns too much detail or noise from the training data, resulting in poor generalization to new data.

What is one method to prevent overfitting?

Cross-validation.

What distinguishes supervised learning from unsupervised learning?

Supervised learning uses labeled data for predictions; unsupervised learning finds patterns in unlabeled data.

What does precision measure in classification metrics?

The number of true positive predictions out of all positive predictions made.

What is the purpose of K-Fold cross-validation?

To ensure that every data point is used for both training and testing, providing a robust performance estimate.

What is the F1 score?

The harmonic mean of precision and recall.

What is tokenization in text preprocessing?

The process of splitting text into individual words or tokens.

What does TF-IDF stand for?

Term Frequency-Inverse Document Frequency.

What is a Random Forest model?

An ensemble method that combines multiple decision trees to improve classification accuracy.

Why is the aggregation step important in Random Forest?

It combines predictions from multiple trees to determine the final output, reducing overfitting and improving accuracy.

What should you prioritize when false positives are costly?

Precision.

What does AUC-ROC measure in model evaluation?

The area under the ROC curve, assessing how well a model distinguishes between different classes.

What does UTXO stand for in the context of Bitcoin?

Unspent Transaction Outputs.

What is mining in the blockchain context?

The process where miners take unconfirmed transactions from the mempool, form a block, and solve a Proof-of-Work (PoW) puzzle to add it to the blockchain.

What is the average time to mine a Bitcoin block?

10 minutes.

What is the maximum supply of Bitcoin?

21 million BTC.

How does Bitcoin determine consensus?

By accepting the longest valid chain.

What type of system does Bitcoin operate on?

Permissionless system where anyone can join.

What is the current reward for mining a block as per the notes?

3.125 BTC.

What is the mempool?

A temporary storage area where unconfirmed transactions wait before being included in a block.

What is overfitting in machine learning?

When a model learns too much detail or noise from the training data, resulting in poor generalization to new data.

What is one method to prevent overfitting?

Cross-validation.

What distinguishes supervised learning from unsupervised learning?

Supervised learning uses labeled data for predictions; unsupervised learning finds patterns in unlabeled data.

What does precision measure in classification metrics?

The number of true positive predictions out of all positive predictions made.

What is the purpose of K-Fold cross-validation?

To ensure that every data point is used for both training and testing, providing a robust performance estimate.

What is the F1 score?

The harmonic mean of precision and recall.

What is tokenization in text preprocessing?

The process of splitting text into individual words or tokens.

What does TF-IDF stand for?

Term Frequency-Inverse Document Frequency.

What is a Random Forest model?

An ensemble method that combines multiple decision trees to improve classification accuracy.

Why is the aggregation step important in Random Forest?

It combines predictions from multiple trees to determine the final output, reducing overfitting and improving accuracy.

What should you prioritize when false positives are costly?

Precision.

What does AUC-ROC measure in model evaluation?

The area under the ROC curve, assessing how well a model distinguishes between different classes.

What is the purpose of splitting data into training and testing sets?

To evaluate the model's performance on unseen data and prevent overfitting.

What is "training data" used for in machine learning?

The dataset used to train a machine learning model, allowing it to learn patterns and relationships.

What is "testing data" used for in machine learning?

The dataset used to evaluate the performance of a trained machine learning model on unseen data.

What is the primary benefit of cross-validation in machine learning?

Provides a more reliable estimate of a model's performance on unseen data by reducing bias and variance in evaluation.

What is stop word removal in text preprocessing?

The process of removing common words (e.g., "the", "a", "is") from text that do not carry significant meaning for analysis.

What is stemming or lemmatization in text preprocessing?

Techniques used to reduce words to their root form (e.g., "running" to "run") to normalize text and reduce vocabulary size.

How can you reduce model complexity in machine learning?

By techniques such as regularization, feature selection, or using simpler model architectures to prevent overfitting.

What is the main goal of machine learning?

To enable systems to learn from data to identify patterns, make predictions, or improve performance on a specific task without explicit programming.

What is "feature engineering" in machine learning?

The process of creating new input features from existing ones to improve the performance of a machine learning model.