In the realm of machine learning, more often than not we think in terms of trade offs. While optimising one metric of performance, we often compromise another performance metric. With the growing evolutionary trend of increasingly larger and more intricate models, understanding, explaining and debugging them become formidable tasks. The intricacies beneath the model's surface, deciphering 'why' our models are making the decisions they are making is vital. Without this clarity how can we confidently ...
Recent Comments