Search Results for author:
Found 6 papers, 1 papers with code
Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement
Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch?
Manas: Mining Software Repositories to Assist AutoML
Recent work on AutoML, more precisely neural architecture search (NAS), embodied by tools like Auto-Keras aims to solve this problem by essentially viewing it as a search problem where the starting point is a default CNN model, and mutation of this CNN model allows exploration of the space of CNN models to find a CNN model that will work best for the problem.
Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules
Also, building a model by reusing or replacing modules can be done with a 2. 3% and 0. 5% average loss of accuracy.
What Do Developers Ask About ML Libraries? A Large-scale Study Using Stack Overflow
Last and somewhat surprisingly, a tug of war between providing higher levels of abstractions and the need to understand the behavior of the trained model is prevalent.
Software Engineering
A Comprehensive Study on Deep Learning Bug Characteristics
The key findings of our study include: data bug and logic bug are the most severe bug types in deep learning software appearing more than 48% of the times, major root causes of these bugs are Incorrect Model Parameter (IPS) and Structural Inefficiency (SI) showing up more than 43% of the times.
Identifying Classes Susceptible to Adversarial Attacks
Based on the distance among original classes, we create mapping among original classes and adversarial classes that helps to reduce the randomness of a model to a significant amount in an adversarial setting.
