We introduce adaptive weight decay, which automatically tunes the
hyper-...
When large scale training data is available, one can obtain compact and
...
Adversarial training has proven to be effective in hardening networks ag...
To deflect adversarial attacks, a range of "certified" classifiers have ...
State-of-the-art adversarial attacks on neural networks use expensive
it...
Adversarial training is one of the strongest defenses against adversaria...
It is well-known that many machine learning models are susceptible to
so...
Transfer learning, in which a network is trained on one task and re-purp...
In this paper, we explore clean-label poisoning attacks on deep convolut...
Adversarial training, in which a network is trained on adversarial examp...
Standard adversarial attacks change the predicted class label of an imag...
A wide range of defenses have been proposed to harden neural networks ag...
School bus planning problem (SBPP) has drawn much research attention due...
Data poisoning is a type of adversarial attack on machine learning model...
Servicing the school transportation demand safely with a minimum number ...
School bus planning is usually divided into routing and scheduling due t...
Bike sharing systems' popularity has consistently been rising during the...