Do wide and deep networks learn the same things? uncovering how neural network representations vary with width and depth
A key factor in the success of deep neural networks is the ability to scale models to improve
performance by varying the architecture depth and width. This simple property of neural …
performance by varying the architecture depth and width. This simple property of neural …
Deep learning through the lens of example difficulty
Existing work on understanding deep learning often employs measures that compress all
data-dependent information into a few numbers. In this work, we adopt a perspective based …
data-dependent information into a few numbers. In this work, we adopt a perspective based …
Membership inference attacks by exploiting loss trajectory
Machine learning models are vulnerable to membership inference attacks in which an
adversary aims to predict whether or not a particular sample was contained in the target …
adversary aims to predict whether or not a particular sample was contained in the target …
Active learning on a budget: Opposite strategies suit high and low budgets
Investigating active learning, we focus on the relation between the number of labeled
examples (budget size), and suitable querying strategies. Our theoretical analysis shows a …
examples (budget size), and suitable querying strategies. Our theoretical analysis shows a …
[HTML][HTML] A wholistic view of continual learning with deep neural networks: Forgotten lessons and the bridge to active and open world learning
Current deep learning methods are regarded as favorable if they empirically perform well on
dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual …
dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual …
Mechanistic Interpretability for AI Safety--A Review
Understanding AI systems' inner workings is critical for ensuring value alignment and safety.
This review explores mechanistic interpretability: reverse-engineering the computational …
This review explores mechanistic interpretability: reverse-engineering the computational …
The lean data scientist: recent advances toward overcoming the data bottleneck
The Lean Data Scientist: Recent Advances Toward Overcoming the Data Bottleneck Page 1
OBTAINING DATA HAS become the key bottleneck in many machine-learning (ML) applications …
OBTAINING DATA HAS become the key bottleneck in many machine-learning (ML) applications …
Characterizing datapoints via second-split forgetting
Researchers investigating example hardness have increasingly focused on the dynamics by
which neural networks learn and forget examples throughout training. Popular metrics …
which neural networks learn and forget examples throughout training. Popular metrics …
Fusing finetuned models for better pretraining
Pretrained models are the standard starting point for training. This approach consistently
outperforms the use of a random initialization. However, pretraining is a costly endeavour …
outperforms the use of a random initialization. However, pretraining is a costly endeavour …
Do input gradients highlight discriminative features?
Post-hoc gradient-based interpretability methods [Simonyan et al., 2013, Smilkov et al.,
2017] that provide instance-specific explanations of model predictions are often based on …
2017] that provide instance-specific explanations of model predictions are often based on …