AI-Accelerated Product Development
Learning N Classes From M<N Samples
Total time needed:
Learn about developments in deep learning research for few-shot learning
Potential Use Cases
In the scenario you too have less than optimal sample sizes!
Who is This For ?
If you're already familiar and have worked with NNs in the past, and looking to navigate suboptimal sample sizes
Click on each of the following
to see details.
1. Dataset Distillation
Is it possible to train a model on synthetic data out of the manifolds of the original data?
How much data is encoded in a given training set and how compressible it is?
2. Soft-Label Dataset Distillation and Text Dataset Distillation
How can we train a model using data distillation and relaxing the hard labels to a probability distribution?
3. ‘Less Than One’-Shot Learning: Learning N Classes From M<N Samples
How can we learn from a dataset that has less classes than what we're hoping to classify?