Despite extensive theoretical work on biologically plausible learning rules, clear evidence about whether and how such rules are implemented in the brain has been difficult to obtain.

An essential question in this framework is how to optimize meta-parameters.

The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of training, is usually adopted. Current methods generally decide the early stopping point by considering a DNN as a whole.

How can artificial agents learn to solve many diverse tasks in complex visual environments without any supervision? We decompose this question into two challenges: discovering new goals and learning to reliably achieve them.

One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning .

Lastly, we demonstrate the superiority of stochastic proximal methods compared to subgradient-based approaches via extensive experiments.

Lastly, we demonstrate the superiority of stochastic proximal methods compared to subgradient-based approaches via extensive experiments.

The temporal trajectories of the variables of the learning problem are modeled by the so called 4th order Cognitive Action Laws (CALs) that come from stationarity conditions of a functional, as it happens for generalized coordinates in classical mechanics.

We present a novel compression algorithm for reducing the storage of LiDAR sensor data streams.

The code is available at LEAStereo.