Using advanced experiments on neuronal cultures and large scale simulations, a group of scientists at Bar-Ilan University in Israel has demonstrated a new type of ultrafast artifical intelligence algorithms — based on the very slow brain dynamics — which outperform learning rates achieved to date by state-of-the-art learning algorithms.
The researchers rebuild the bridge between neuroscience and advanced artificial intelligence algorithms that has been left virtually useless for almost 70 years.
Compared with the existing artificial intelligence algorithms, asynchronous input based biological learning schemes can improve the scaling of learning rates of feedforward networks.
Results suggest that faster learning rates can be achieved with dendritic adaptation in comparison to a traditional synchronous perceptron. In addition, an extension of the fast learning rates to multi-layer networks is also discussed. The paper concludes with guidelines for fundamental questions in the future regarding the development of advanced classes of deep learning algorithms.
The simulation results of biological learning algorithms show state-of-the-art optimal learning curves in supervised learning of feedforward networks. The biological learning algorithms comprise asynchronous input signals with decaying input summation, weights adaptation, and multiple outputs for an input signal. In particular, the generalization error for such biological perceptrons decreases rapidly with increasing number of examples, and it is independent of the size of the input. This is achieved using either synaptic learning, or solely through dendritic adaptation with a mechanism of swinging between reflecting boundaries, without learning steps. The proposed biological learning algorithms outperform the optimal scaling of the learning curve in a traditional perceptron. It also results in a considerable robustness to disparity between weights of two networks with very similar outputs in biological supervised learning scenarios. The simulation results indicate the potency of neurobiological mechanisms and open opportunities for developing a superior class of deep learning algorithms.