emlearn is an open-source machine learning inference engine designed for microcontrollers and embedded devices. It supports various machine learning models for classification, regression, unsupervised learning, and feature extraction. The engine is portable, with a single header file include, and uses C99 code and static memory allocation. Users can train models in Python and convert them to C code for inference.
A ready-to-run tutorial in Python and scikit-learn to evaluate a classification model compared to a baseline model
LLMS popularized zero-shot learning, or "prompt engineering" which is drastically easier to use and more effective than labeling data. You can also retrofit "prompt engineering" onto good old fashion ML like text classifiers.
Zero-Shot Classification
To perform zero shot classification, we want to predict labels for our samples without any training. To do this, we can simply embed short descriptions of each label, such as positive and negative, and then compare the cosine distance between embeddings of samples and label descriptions.
As shown above, zero-shot classification with embeddings can lead to great results, especially when the labels are more descriptive than just simple words.
The highest similarity label to the sample input is the predicted label. We can also define a prediction score to be the difference between the cosine distance to the positive and to the negative label. This score can be used for plotting a precision-recall curve, which can be used to select a different tradeoff between precision and recall, by selecting a different threshold.
To perform zero shot classification, we want to predict labels for our samples without any training. To do this, we can simply embed short descriptions of each label, such as positive and negative, and then compare the cosine distance between embeddings of samples and label descriptions.
As shown above, zero-shot classification with embeddings can lead to great results, especially when the labels are more descriptive than just simple words.
The highest similarity label to the sample input is the predicted label. We can also define a prediction score to be the difference between the cosine distance to the positive and to the negative label. This score can be used for plotting a precision-recall curve, which can be used to select a different tradeoff between precision and recall, by selecting a different threshold.
Multi-Label Classification with Deep Learning
