Contact Us

Comments

Post a Comment

Popular posts from this blog

Model Drift in Machine Learning

Image
  We expect our model to perform the same as it does with the training data. However if the distribution of production data is different from that of the training data, this may lead to Model Drift. Model drift refers to the decay of the model’s predictive power. Model Drift occurs when: Training data is poorly sampled There is a change in the underlying business context Why is important to monitor Model Drift? It is necessary to monitor performance for model drift to ensure accurate predictions and check if retraining is required. Kinds of Drift Data Drift/Feature drift   — When there is a change in the input feature. Ta rget Drift   — When there is a change in the distribution of the target variable. Concept Drift   — When there is a change between the pattern or the relationship between the predictors and the outcome. Data Drift: This is also known as feature drift, population drift or covariate drift. Data drift is observed when there is a change in the distribut...
Read more

Brain Teasers | Tiger and Sheep

Image
Question:   One hundred tigers and one sheep arc are put on a magic island that only has grass. Tigers can eat grass, but they would rather eat sheep Assume:    A. Each time only one tiger can eat one sheep, and that tiger itself will become a sheep after it cats the sheep.    B. All tigers are smart and perfectly rational and they want to survive. So will the sheep be eaten?      Solution :     Let no of tigers = n     Let's start with 1 tiger(n=1).   Since there is only one tiger it will definitely eat the sheep as there will be no more tigers to eat him once he becomes a sheep.       With n=2 tigers,   If any of the tigers eat the sheep, it will become a sheep itself so the other tiger who is left will definitely eat him. So none of the tigers will eat the sheep.     With n=3 tigers,   The sheep will be eaten since each tiger realizes that once it becomes a sheep there will be two tige...
Read more

Model Cards for Model Reporting

Image
  What are model cards? Today machine learning models have a lot of potentials. Knowing about the usage and limitations of a model is crucial. Model cards aim to provide that information in a holistic and comprehensive way. They contain short records of various aspects of ML models. Why do we need model cards? Lack of documentation: Due to lack of documentation users might not be aware of the valid uses. This can have a serious impact in areas like — Healthcare, law and order, employment etc. For example — If a healthcare model is trained on da t a pertaining to specific geography (assume Indians) it might not be applicable to the American population. Hence the model should not be used in the treatment of American patients. Due to lack of documentation often important information like the kind of data used in training the model seems to be missing. Lack of transparency: Often machine learning models do not state the ethical considerations clearly. This can also lead to systematic b...
Read more