According to the “No Free Lunch” theorem, there is no one model that works best for every problem. A model which may be great for one problem may not hold for another problem at all.
According to the “No Free Lunch” theorem, there is no one model that works best for every problem. A model which may be great for one problem may not hold for another problem at all.
In supervised machine learning, generalization error is a measure of how accurately an algorithm is able to predict outcome values for previously unseen data.
In supervised machine learning, generalization error is a measure of how accurately an algorithm is able to predict outcome values for previously unseen data.
Entropy is a measure of the randomness in the information being processed. The higher the entropy, the harder it is to draw any conclusions from that information. The concept of entropy is used in decision tree development to identify the variable related to the branching node.
Entropy is a measure of the randomness in the information being processed. The higher the entropy, the harder it is to draw any conclusions from that information. The concept of entropy is used in decision tree development to identify the variable related to the branching node.
High bias and low variance algorithms train models that are consistent, but inaccurate on average. High variance and low bias algorithms train models that are accurate but inconsistent. if we make the model more complex by adding more variables, we will lose bias but gain variance. To get the optimaRead more
High bias and low variance algorithms train models that are consistent, but inaccurate on average.
High variance and low bias algorithms train models that are accurate but inconsistent.
if we make the model more complex by adding more variables, we will lose bias but gain variance.
To get the optimally-reduced amount of error, we will have to trade off bias and variance. Neither high bias nor high variance is desired.
It depends upon the research question and type of data available for training. If we are looking for cluster or pattern identification, we go with unsupervised machine learning where as if we are looking for outcome to be a category or regression, we go with supervised machine learning using traininRead more
It depends upon the research question and type of data available for training. If we are looking for cluster or pattern identification, we go with unsupervised machine learning where as if we are looking for outcome to be a category or regression, we go with supervised machine learning using training data having labelled outcome variable.
What is design of experiment?
swain
It is the initial process which is used to split data, data sampling or data setup for statistical analysis.
It is the initial process which is used to split data, data sampling or data setup for statistical analysis.
See lessWhat is KPI?
swain
KPI or Key Performance Indicator can be defined as the metric which consists of a combination of charts, reports, spreadsheets or business processes.
KPI or Key Performance Indicator can be defined as the metric which consists of a combination of charts, reports, spreadsheets or business processes.
See lessWhat is “No Free Lunch” theorem in Machine Learning?
swain
According to the “No Free Lunch” theorem, there is no one model that works best for every problem. A model which may be great for one problem may not hold for another problem at all.
According to the “No Free Lunch” theorem, there is no one model that works best for every problem. A model which may be great for one problem may not hold for another problem at all.
See lessWhat is generalization error?
swain
In supervised machine learning, generalization error is a measure of how accurately an algorithm is able to predict outcome values for previously unseen data.
In supervised machine learning, generalization error is a measure of how accurately an algorithm is able to predict outcome values for previously unseen data.
See lessWhat is the importance on entropy in machine learning?
swain
Entropy is a measure of the randomness in the information being processed. The higher the entropy, the harder it is to draw any conclusions from that information. The concept of entropy is used in decision tree development to identify the variable related to the branching node.
Entropy is a measure of the randomness in the information being processed. The higher the entropy, the harder it is to draw any conclusions from that information. The concept of entropy is used in decision tree development to identify the variable related to the branching node.
See lessHow do you do a trade-off between bias and variance in machine learning
swain
High bias and low variance algorithms train models that are consistent, but inaccurate on average. High variance and low bias algorithms train models that are accurate but inconsistent. if we make the model more complex by adding more variables, we will lose bias but gain variance. To get the optimaRead more
High bias and low variance algorithms train models that are consistent, but inaccurate on average.
High variance and low bias algorithms train models that are accurate but inconsistent.
if we make the model more complex by adding more variables, we will lose bias but gain variance.
See lessTo get the optimally-reduced amount of error, we will have to trade off bias and variance. Neither high bias nor high variance is desired.
If the training dataset is very small, what is the importance of bias and variance while selecting machine learning algorithm?
swain
If the training dataset is small, a model having high bias and low variance seems to work better because they are less likely to over fit.
If the training dataset is small, a model having high bias and low variance seems to work better because they are less likely to over fit.
See lessBased on the business needs, how will you decide to select supervised or unsupervised machine learning algorithm
swain
It depends upon the research question and type of data available for training. If we are looking for cluster or pattern identification, we go with unsupervised machine learning where as if we are looking for outcome to be a category or regression, we go with supervised machine learning using traininRead more
It depends upon the research question and type of data available for training. If we are looking for cluster or pattern identification, we go with unsupervised machine learning where as if we are looking for outcome to be a category or regression, we go with supervised machine learning using training data having labelled outcome variable.
See lessWhat is the difference between K means and KNN clustering
swain
K-means -(1) Unsupervised machine learning (2) Cluster algorithm KNN- (1) Supervised machine learning (2) Classification algorithm
K-means -(1) Unsupervised machine learning (2) Cluster algorithm
See lessKNN- (1) Supervised machine learning (2) Classification algorithm
What is the difference between K means and KNN clustering
swain
K-means -(1) Unsupervised machine learning (2) Cluster algorithm KNN- (1) Supervised machine learning (2) Classification algorithm
K-means -(1) Unsupervised machine learning (2) Cluster algorithm
See lessKNN- (1) Supervised machine learning (2) Classification algorithm