Search Results for author:
Found 21 papers, 10 papers with code
Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce Tasks
Medical datasets often face the problem of data scarcity, as ground truth labels must be generated by medical professionals.
How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?
Model robustness is vital for the reliable deployment of machine learning models in real-world applications.
A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges
We believe that this technical review can help to promote a sustainable development of AI R&D activities for the research community.
ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning
The ability to reason with multiple hierarchical structures is an attractive and desirable property of sequential inductive biases for natural language processing.
FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding
Moreover, we show that the FASTTREES module can be applied to enhance Transformer models, achieving performance gains on three sequence transduction tasks (machine translation, subject-verb agreement and mathematical language understanding), paving the way for modular tree induction modules.
On Orthogonality Constraints for Transformers
Orthogonality constraints encourage matrices to be orthogonal for numerical stability.
Deep Extrapolation for Attribute-Enhanced Generation
Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution.
RNA Alternative Splicing Prediction with Discrete Compositional Energy Network
In the case of alternative splicing prediction, DCEN models mRNA transcript probabilities through its constituent splice junctions' energy values.
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters
Recent works have demonstrated reasonable success of representation learning in hypercomplex space.
Recurrently Controlling a Recurrent Network with Recurrent Networks Controlled by More Recurrent Networks
This paper explores an intriguing idea of recursively parameterizing recurrent nets.
Parameterization of Hypercomplex Multiplications
Recent works have demonstrated reasonable success of representation learning in hypercomplex space.
Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder
This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems.
Player Identification in Hockey Broadcast Videos
We propose an end-to-end trainable ResNet+LSTM network, with a residual network (ResNet) base and a long short-term memory (LSTM) layer, to discover spatio-temporal features of jersey numbers over time and learn long-term dependencies.
Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences
Understanding human preferences, along with cultural and social nuances, lives at the heart of natural language understanding.
CoCon: A Self-Supervised Approach for Controlled Text Generation
While there are studies that seek to control high-level attributes (such as sentiment and topic) of generated text, there is still a lack of more precise control over its content at the word- and phrase-level.
Metagross: Meta Gated Recursive Controller Units for Sequence Modeling
This paper proposes Metagross (Meta Gated Recursive Controller), a new neural sequence modeling unit.
Jacobian Adversarially Regularized Networks for Robustness
Adversarial examples are crafted with imperceptible perturbations with the intent to fool neural networks.
What it Thinks is Important is Important: Robustness Transfers through Input Gradients
Learned weights of models robust to such perturbations are previously found to be transferable across different tasks but this applies only if the model architecture for the source and target tasks is the same.
Poison as a Cure: Detecting & Neutralizing Variable-Sized Backdoor Attacks in Deep Neural Networks
Existing defenses are effective under certain conditions such as a small size of the poison pattern, knowledge about the ratio of poisoned training samples or when a validated clean dataset is available.
R2D2: Reuse & Reduce via Dynamic Weight Diffusion for Training Efficient NLP Models
We propose R2D2 layers, a new neural block for training efficient NLP models.
Metamorphic Relation Based Adversarial Attacks on Differentiable Neural Computer
Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks.
