Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

COSC 105 - Intelligent Systems > Finals Lectures > Flashcards

Finals Lectures Flashcards

1
Q

Identify

System of interconnected neurons that mimics the human brain’s ability to process information

2 words

NEURAL NETWORK

A

Neural Network

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Identify

Can recognize patterns and correlations in raw data, cluster and classify it, and continuously learn and improve.

2 words

NEURAL NETWORK

A

Neural Network

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Identify

Basic building block of a neural network, modeled after biological neurons in the human brain.

1 word

NEURAL NETWORK

A

Neuron

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Identify

Receives inputs, processes them by applying weights and biases, and passes the result through an activation function to produce an output.

1 word

NEURAL NETWORK

A

Neuron (Function)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Identify

Parameters in a neural network that determine the importance of each input.

1 word

NEURAL NETWORK

A

Weights

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Identify

They scale the input values before they are summed up in the neuron. Inputs with higher weights contribute more to the neuron’s decision.

1 word

NEURAL NETWORK

A

Weights (Purpose)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Identify

Constant value added to the weighted sum of inputs before applying the activation function.

1 word

NEURAL NETWORK

A

Bias

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Identify

It helps shift the activation function curve to better fit the data, allowing the model to represent patternsmore flexibly.

1 word

NEURAL NETWORK

A

Bias (Purpose)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Identify

Determines whether a neuron ‘fires’ and produces an output.

2 words

NEURAL NETWORK

A

Activation Function

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Identify

It introduces non-linearity into the network, enabling it to learn complex patterns.

2 words

NEURAL NETWORK

A

Activation Function

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Identify

Produces outputs between 0 and 1, useful for probabilities.

2 words

NEURAL NETWORK - Common Activation Function

A

Sigmoid Function

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Identify

Outputs the input directly if it’s positive; otherwise, 0.

3 words or shortened 1 word

NEURAL NETWORK - Common Activation Function

A

ReLU (Rectified Linear Unit)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Identify

Training, validation, and test sets.

1 word

NEURAL NETWORK - Common Activation Function

A

Dataset

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Identify

Data flows through the network.

2 words

NEURAL NETWORK - Common Activation Function

A

Forward Propagation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Identify

Adjusts weights using the error gradient.

2 words

NEURAL NETWORK - Common Activation Function

A

Backward Propagation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Identify

Repeated adjustments to improve performance.

1 word

NEURAL NETWORK - Common Activation Function

A

Iterations (Epochs)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Identify

Simplest type of neural network.

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Feedforward Neural Network (FNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Identify

information flows in one direction—from input to output

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Feedforward Neural Network (FNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Identify

Used for tasks where inputs and outputs are straightforward.

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Feedforward Neural Network (FNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Identify

No complex patterns or sequences are involved; it just maps input data to output values.

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Feedforward Neural Network (FNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Identify (Example)

Predicting house prices

1 word

NEURAL NETWORK - Types of Neural Network

A

Task (Feedforward Neural Network (FNN))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Identify (Example)

House size, number of bedrooms, location rating.

1 word

NEURAL NETWORK - Types of Neural Network

A

Inputs (Feedforward Neural Network (FNN))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Identify (Example)

Estimated price of the house.

1 word

NEURAL NETWORK - Types of Neural Network

A

Output (Feedforward Neural Network (FNN))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Identify

Specially designed for image and video data.

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Convolutional Neural Networks (CNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Identify

Recognizes patterns, edges, and features in visuals by applying filters.

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Convolutional Neural Networks (CNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

Identify

It’s excellent at analyzing spatial features like shapes, textures, and colors in images.

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Convolutional Neural Networks (CNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

Identify (Example)

Identifying cats and dogs in pictures.

1 word

NEURAL NETWORK - Types of Neural Network

A

Task (Convolutional Neural Networks (CNN))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Identify (Example)

Images of animals

1 word

NEURAL NETWORK - Types of Neural Network

A

Inputs (Convolutional Neural Networks (CNN))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

Identify (Example)

Label (“Cat” or “Dog”)

1 word

NEURAL NETWORK - Types of Neural Network

A

Output (Convolutional Neural Networks (CNN))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Identify

Processes sequential data by remembering past inputs while processing current ones

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Recurrent Neural Network (RNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Identify

Useful for tasks where the order of data matters

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Recurrent Neural Network (RNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Identify

It can retain information about previous words to make the prediction contextually accurate

3 words or abbreviation

NEURAL NETWORK - Types of Neural Network

A

Recurrent Neural Network (RNN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

Identify (Example)

Predicting the next word in a sentence.

1 word

NEURAL NETWORK - Types of Neural Network

A

Task (Predicting the next word in a sentence.)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Identify (Example)

A sequence of words like “I love neural…”

1 word

NEURAL NETWORK - Types of Neural Network

A

Inputs (Predicting the next word in a sentence.)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

Identify (Example)

Predicted word (“networks”).

1 word

NEURAL NETWORK - Types of Neural Network

A

Output (Predicting the next word in a sentence.)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

Identify

Process of discovering patterns in large datasets.

2 words

Data Mining

A

Data Mining

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

Identify

It’s a multidisciplinary field that uses techniques from machine learning, statistics and database systems.

2 words

Data Mining

A

Data Mining

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

Fill in the blanks

Extract ? information

1 word

Data Mining - Goals

A

useful

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
39
Q

Fill in the blanks

Make ? decisions

2 words

Data Mining - Goals

A

data-driven

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
40
Q

Identify

Organized and easy to search and analyze because it is stored in predefined formats.

2 words

Data Mining - Types of Data

A

Structured Data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
41
Q

Identify

It has rows and columns, with each column assigned a specific type of data.

2 words

Data Mining - Types of Data

A

Structured Data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
42
Q

Identify

Does not have a fixed format, making it harder to organize and analyze directly.

2 words

Data Mining - Types of Data

A

Unstructured Data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
43
Q

Identify

It can include text, images, audio, video, or any other data format that doesn’t fit neatly into rows and columns.

2 words

Data Mining - Types of Data

A

Unstructured Data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
44
Q

Identify

The crucial first step in any data analysis or machine learning pipeline.

2 words

Data Mining

A

Data Preprocessing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
45
Q

Identify

It involves cleaning, organizing, and transforming raw data into a usable format for analysis.

2 words

Data Mining

A

Data Preprocessing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
46
Q

Identify

? is often incomplete, noisy, or inconsistent, making it difficult to analyze or use effectively.

2 words

Data Mining - Data Preprocessing

A

Raw data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
47
Q

Identify

? ensures the quality, reliability, and performance of your models.

2 words

Data Mining - Data Preprocessing

A

Proper preprocessing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
48
Q

Identify

replace missing values with mean/median (for numerical data) or mode (for categorical data), or remove rows/columns with too many missing values.

2 words and 3 words (Key Step Term and Term under it)

Data Mining - Key Steps in Data Preprocessing

A

Data Cleaning (Handling Missing Values)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
49
Q

Identify

Eliminate irrelevant data points, outliers, or duplicates.

2 words and 2 words (Key Step Term and Term under it)

Data Mining - Key Steps in Data Preprocessing

A

Data Cleaning (Removing Noise)

50
Q

Identify

Combine data from multiple sources

2 words

Data Mining - Key Steps in Data Preprocessing

A

Data Integration

51
Q

Identify (Example)

Combine data from multiple sources

1 word

Data Mining - Key Steps in Data Preprocessing

A

Tasks (Data Integration)

52
Q

Identify

Convert data into a format suitable for analysis or modeling.

2 words

Data Mining - Key Steps in Data Preprocessing

A

Data Transformation (Objective )

53
Q

Identify

Scale numerical data to a common range (e.g., 0 to 1).

1 word

Data Mining - Key Steps in Data Preprocessing - Objective Tasks

A

Normalization

54
Q

Identify

Convert continuous data into discrete categories (e.g., age groups).

1 word

Data Mining - Key Steps in Data Preprocessing - Objective Tasks

A

Discretization

55
Q

Identify

Reduce the size of data while maintaining essential information

2 words

Data Mining - Key Steps in Data Preprocessing

A

Data Reduction (Objective)

56
Q

Identify

Use techniques like Principal Component Analysis (PCA) to reduce the number of features.

2 words

Data Mining - Key Steps in Data Preprocessing - Data Reduction Tasks

A

Dimensionality Reduction

57
Q

Identify

Use techniques like Principal Component Analysis (PCA) to reduce the number of features.

2 words

Data Mining - Key Steps in Data Preprocessing - Data Reduction Tasks

A

Dimensionality Reduction

58
Q

Identify

Select only the most relevant attributes for analysis.

2 words

Data Mining - Key Steps in Data Preprocessing - Data Reduction Tasks

A

Feature Selection

59
Q

Identify

Supervised machine learning technique used to predict the category or label of data points based on input features.

1 word

Data Mining - Classification

A

Classification

60
Q

Identify

It requires a training dataset with predefined labels

1 word

Data Mining - Classification

A

Classification

61
Q

Enumerate (Examples)

Classification Examples

Examples only

Data Mining - Classification

A
  • Email spam detection
  • Loan approval
62
Q

Enumerate (Examples)

Classification Techniques

Examples only

Data Mining - Classification

A
  • Decision Trees
  • Naïve
  • Bayes
  • Support Vector Machines (SVM)
63
Q

Enumerate (Examples)

Classification Evaluation

Examples only

Data Mining - Classification

A
  • Accuracy
  • Precision
  • Recall
  • F1-score
64
Q

Identify

Unsupervised machine learning technique that groups similar data points into clusters.

1 word

Data Mining - Clustering

A

Clustering

65
Q

Enumerate (Examples)

Clustering Examples

Examples

Data Mining - Clustering

A
  • Customer segmentation
  • Image segmentation
66
Q

Enumerate (Examples)

Clustering Techniques

Examples

Data Mining - Clustering

A
  • K-Means
  • Hierarchical
  • Clustering
  • DBSCAN
67
Q

Explain

Clustering Evaluation

Examples

Data Mining - Clustering

A

Choosing the right number of clusters

68
Q

Identify

Technique to discover interesting relationships or patterns between items in a dataset.

3 words

Data Mining - Association Rule Mining

A

Association Rule Mining

69
Q

Identify

It is commonly used in market basket analysis.

3 words

Data Mining - Association Rule Mining

A

Association Rule Mining

70
Q

Enumerate (Examples)

Association Rule Mining (Examples)

Examples

Data Mining - Association Rule Mining

A
  • Market Basket Analysis
  • Online Recommendations
71
Q

Identify

Frequency of an itemset in the dataset.

1 word

Data Mining - Association Rule Mining - Key concepts

A

Support

72
Q

Identify

Strength of a rule (e.g., if A, then B).

1 word

Data Mining - Association Rule Mining - Key concepts

A

Confidence

73
Q

Identify

Measures how much more likely two items are bought together than if they were independent.

1 word

Data Mining - Association Rule Mining - Key concepts

A

Lift

74
Q

Identify

Machine learning technique that uses labeled data to train algorithms.

2 words

Supervised Learning

A

Supervised Learning

75
Q

Identify

? are trained using input objects and desired output values, often human-made labels.

3 words

Supervised Learning

A

Supervised learning models

76
Q

Identify

Can identify and classify spam emails.

2 words

Supervised Learning - Applications

A

Spam filtering

77
Q

Identify

Can automatically classify images into different categories.

2 words

Supervised Learning - Applications

A

Image classification

78
Q

Identify

Can analyze patient data to identify patterns that suggest specific diseases or conditions.

2 words

Supervised Learning - Applications

A

Medical diagnosis

79
Q

Identify

Can analyze financial transactions to identify patterns that indicate fraudulent activity.

2 words

Supervised Learning - Applications

A

Fraud detection

80
Q

Identify

Models can overfit training data, leading to poor performance on new data.

1 word

Supervised Learning - Challenges

A

Overfitting

81
Q

Identify

Bias in the training data may result in unfair predictions.

3 words

Supervised Learning - Challenges

A

Bias in models

82
Q

Identify

Labeled training data can be costly and time-consuming to obtain.

4 words

Supervised Learning - Challenges

A

Dependence on labeled data

83
Q

Identify

Missing data can disrupt model training

3 words

Supervised Learning - Data Preprocessing

A

Handle Missing Values

84
Q

Identify

Replacing missing values with the mean (for numerical data) or mode (for categorical data) maintains dataset integrity

3 words

Supervised Learning - Data Preprocessing

A

Handle Missing Values

85
Q

Identify

Supervised learning models require numerical inputs.

3 words

Supervised Learning - Data Preprocessing

A

Encode Categorical Variables

86
Q

Identify

Transforming categorical data into numeric form allows the model to interpret them.

3 words

Supervised Learning - Data Preprocessing

A

Encode Categorical Variables

87
Q

Identify

Different features often have varying magnitudes (e.g., age in years vs. salary in thousands).

2 words

Supervised Learning - Data Preprocessing

A

Feature Scaling

88
Q

Identify

Algorithms like Logistic Regression or SVM are sensitive to these differences, as they **rely on distance or gradient-based optimization. **

2 words

Supervised Learning - Data Preprocessing

A

Feature Scaling

89
Q

Identify

Scaling ensures equal importance for all features

2 words

Supervised Learning - Data Preprocessing

A

Feature Scaling

90
Q

Identify

Separates the dataset into training and testing subsets.

2 words

Supervised Learning - Data Preprocessing

A

Data Splitting

91
Q

Identify

? is used to build the model, and testing data evaluates its performance.

2 words

Supervised Learning - Data Preprocessing - Data Splitting

A

Training data

92
Q

Identify

Used for binary classification problems (e.g., Yes/No, 0/1).

2 words

Supervised Learning - Logistic Regression

A

Logistic Regression

93
Q

Identify

Estimates the probability of an observation belonging to a specific category by using the logistic function (sigmoid function).

2 words

Supervised Learning - Logistic Regression

A

Logistic Regression

94
Q

Identify

The ? maps predictions to a range between 0 and 1, making it interpretable as a probability.

2 words

Supervised Learning - Logistic Regression

A

sigmoid function

95
Q

Identify

Powerful supervised learning algorithm used for classification and regression tasks.

3 words

Supervised Learning - Support Vector Machine

A

Support Vector Machine

96
Q

Identify

In classification, SVM aims to find the hyperplane that best separates the data into different classes.

3 words

Supervised Learning - Support Vector Machine

A

Support Vector Machine

97
Q

Identify

The ? is the line (in 2D) or a plane (in 3D) that divides the feature space into regions corresponding to different classes.

1 word

Supervised Learning - Support Vector Machine

A

hyperplane

98
Q

Identify

The model seeks to maximize the margin, which is the distance between the hyperplane and the closest data points from each class, called ?.

2 words

Supervised Learning - Support Vector Machine

A

support vectors

99
Q

Identify

You have points in a feature space (2D or higher) where each point belongs to a certain class.

2 words

Supervised Learning - Support Vector Machine - Key Components

A

Data Points

100
Q

Identify

Each point belongs to one of the categories (like Class A or Class B).

1 word

Supervised Learning - Support Vector Machine - Key Components

A

Classes

101
Q

Identify

SVM finds a line (in 2D) or plane (in higher dimensions) that separates the data points into different classes.

1 word

Supervised Learning - Support Vector Machine - Key Components

A

Hyperplane

102
Q

Identify

The points closest to the decision boundary (line) that help determine the position of the hyperplane.

2 words

Supervised Learning - Support Vector Machine - Key Components

A

Support Vectors

103
Q

Fill in the blanks

The SVM model is ? using a dataset.

1 word

Supervised Learning - Support Vector Machine - Steps - Training

A

trained

104
Q

Fill in the blanks

Once trained, the SVM can ? which side of the line a new data point falls into—whether it belongs to Class A or Class B.

1 word

Supervised Learning - Support Vector Machine - Steps - Evaluation

A

predict

105
Q

Identify

Works by splitting the dataset into subsets based on feature values.

2 words

Supervised Learning - Decision Tree

A

Decision Tree

106
Q

Identify

The process continues until the model achieves a desired level of purity (where all samples in a subset belongs to the same class) or reaches a stopping criterion (e.g., maximum depth).

2 words

Supervised Learning - Decision Tree

A

Decision Tree

107
Q

Identify

The dataset is split based on conditions, like “Is Age > 30?” or “Is Salary > 50,000?”.

1 word

Supervised Learning - Decision Tree - How it Works

A

Splitting

108
Q

Identify

? are made to maximize information gain (classification) or minimize variance (regression).

1 word

Supervised Learning - Decision Tree - How it Works

A

Splitting

109
Q

Identify

Each split leads to a ?. Nodes represent questions based on features.

2 words

Supervised Learning - Decision Tree - How it Works

A

Decision Nodes

110
Q

Identify

These are the final nodes that predict a class label (for classification) or a continuous value (for regression).

2 words

Supervised Learning - Decision Tree - How it Works

A

Leaf Nodes

111
Q

Identify

Determines how splits are made (e.g., “gini” for Gini Impurity or “entropy” for Information Gain).

1 word

Supervised Learning - Decision Tree - How it Works - Key Parameters

A

Criterion

112
Q

Identify

Limits the depth of the tree to avoid overfitting.

2 words

Supervised Learning - Decision Tree - How it Works - Key Parameters

A

Max Depth

113
Q

Identify

Minimum samples required to split a node.

3 words

Supervised Learning - Decision Tree - How it Works - Key Parameters

A

Min Samples Split

114
Q

Identify

Measures overall correctness by comparing correct predictions to total predictions.

1 word

Supervised Learning - Evaluating Models - Metrics

A

Accuracy

115
Q

Identify

Useful when class distributions are balanced.

1 word

Supervised Learning - Evaluating Models - Metrics

A

Accuracy

116
Q

Identify

Calculates the proportion of true positives among predicted positives.

1 word

Supervised Learning - Evaluating Models - Metrics

A

Precision

117
Q

Identify

Prioritize this when false positives are more costly (e.g., spam detection).

1 word

Supervised Learning - Evaluating Models - Metrics

A

Precision

118
Q

Identify

Measures sensitivity or the ability to identify all actual positives.

1 word

Supervised Learning - Evaluating Models - Metrics

A

Recall

119
Q

Identify

Useful when missing positives has severe consequences (e.g., medical diagnosis).

1 word

Supervised Learning - Evaluating Models - Metrics

A

Recall

120
Q

Identify

Provides a balance between precision and recall, especially when classes are imbalanced.

2 words

Supervised Learning - Evaluating Models - Metrics

A

F1-Score

121
Q

Identify

A simple way to evaluate how well a classification model works by showing the actual and predicted results in a table.

2 words

Supervised Learning - Confusion Matrix

A

Confusion Matrix

COSC 105 - Intelligent Systems (4 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions