2 citations · 4 across the 8 of their papers we have counts for
4 papers · 1 filter
Using linear initialisation to improve speed of convergence and fully-trained error in Autoencoders
Marcel Marais, Mate Hartstein, George Cevora
Good weight initialisation is an important step in successful training of Artificial Neural Networks. Over time a number of improvements have been proposed to this process. In this…
Instability of computer vision models is a necessary result of the task itself
Oliver Turnbull, George Cevora
Adversarial examples resulting from instability of current computer vision models are an extremely important topic due to their potential to compromise any application. In this pap…
Achieving Stable Training of Reinforcement Learning Agents in Bimodal Environments through Batch Learning
E. Hurwitz, N. Peace, G. Cevora
Bimodal, stochastic environments present a challenge to typical Reinforcement Learning problems. This problem is one that is surprisingly common in real world applications, being p…
Explainable AI does not provide the explanations end-users are asking for
Savio Rozario, George Čevora
Explainable Artificial Intelligence (XAI) techniques are frequently required by users in many AI systems with the goal of understanding complex models, their associated predictions…