LU 2 Flashcards
What is concept learning
Describes the process where experience allows us to partition objects in the world into classes for the purpose of generalization, discrimination and inference
(the process of gaining knowledge or skill by studying practicing or being taught)
what is concept learning in terms of machine learning
Teaching machine to distinguish between examples and non- examples of ideas such as symphony, anger etc
Fill in the words
____can be seen as a problem of searching through a predefined space of potential
hypotheses for the hypothesis that best fits the training examples
concept learning
in concept learning what does the target concept refer to?
The concept or function to be learned (denoted by c (c:x->{0,1})
what is object recognition
a computer vision technique for identifying objects in images or videos
What is object detection
The process of finding instances of objects in images , a subset of object recognition) objects are also found inside the images
what is a deep learning model that can be used to identify objects?
Convolutional neural networks (CNN)
what are the two approaches to performing object recognition using deep learning
- Training model from scratch by feeding it a large labeled dataset and design a network architecture that learns the features and build the model
- use a pretrained deep learning model such as AlexNet or GoogleNet
name an example of machine learning techniques for object recognition
- HOG feature extraction with an SVM machine learning model
- Bag-of-words models with features such as SURF and MSER
how would you perform object recognition using a standard machine learning approach
start with a collection of images and select the relevant features in each image
if you have a lot of data and no powerful GPU should you use a machine learning technique or a deep learning technique to train a model
machine learning
what is the difference between deep learning and a neural network
Deep learning- deep refers to the depth of layers in a neural network - consisting of more than three layers
a neural network has only two or three layers
what are concept feature spaces?
the set of all possible values for a chosen set of features from that data.
refers to the collections of features that are used to characterize your data
what is a feature in terms of concept feature spaces?
a column or attribute that you’ll use to model your problem excluding the target variable
when is concept feature spaces used?
In machine learning (because it is feature extraction)
what does n mean in concept feature spaces?
n refers to the number of features
Explain what happens to the cases if the features space gets bigger
the cases get further apart from each other and there is more empty space between them
What is a decision tree
It is hierarchical tree structure that consists of root node, branches internal nodes and leaf nodes
when do you use a decision tree?( what type of task)
– classification
–regression
both
what does the nodes in a decision tree represent
a test on an attribute
what does each leaf node in a decision tree represent
classification rules
what does a branch in a decision tree represent
the outcome of the test
Why would you use a decision tree
to predict class or value of target variables in supervised learning regression and classification algorithms
give some examples of when decision trees are used
- risk management
healthcare
capital budgeting
finance
what are some advantages of decision trees
easy to interpret (boolean logic)
little to no data preparation required(can handle various data types)
more flexible( both classification as well as regression)
what are some disadvantages of decision trees
prone to overfitting
high variance estimators
more costly
not fully supported in scikit-learn
