4.3. Experiments and Results 4 45 = 17.59). Notably, the model adopted an encoding strategy where the presence of the alphabetic character (white pixels) is encoded with the absence of phosphenes and vice versa, resulting in an average electrode activity (percentage of active electrodes) of 95.65%. Such an ‘inverted’ encoding strategy was found for two out of the five random restart initializations and observed for all 234 images in the validation dataset. Figure 4.3: Results of experiment 1. The model was trained to minimize mean squared error loss. (a) The training curves indicating the loss on the training dataset and validation dataset during the training procedure. (b) Visualization of the network input (left) the simulated prosthetic vision (middle) and the reconstruction (right). 4.3.3. Experiment 2 In the second experiment, we assess whether our model allows the inclusion of additional constraints. To exemplify this advantage of our proposed approach, we chose to evaluate the effects of adding a sparsity loss term. Considering the potentially adverse effects of electrical stimulation (Lewis et al., 2015; McCreery et al., 1988), one might want to introduce such a sparsity requirement that constrains the stimulation protocol, limiting the neural degradation by enforcing minimal energy transfer to neural tissue. Let s =(s1,...,sM) denote a stimulation vector representing the stimulation pattern for M electrodes. We define sparsity as the L1 norm on the stimulation protocol: LS = 1 / N NX n=1 ∥s(n)∥ (4.2) wheres(n) is the stimulation vector for then-th training example. The objective is to minimize the total loss Ltotal =(1−κ)LI +κLS (4.3)
RkJQdWJsaXNoZXIy MTk4NDMw