Abstract: A processor-implemented method with checkpointing includes: performing an operation for learning of an artificial neural network (ANN) model; and performing a checkpointing to store information about a state of the ANN model, simultaneously with performing the operation for the learning of the ANN model.

Abstract: A stacked IC package includes a first die including a first power transmission region, an adapter die stacked on the first die, a second die stacked on the adapter die and including a second power transmission region, and a first power transmission path electrically connected between the second power transmission region and the first power transmission region through the adapter die. The first power transmission path includes a first power transmission part penetrating a portion of the adapter die in a vertical direction from the first power transmission region, a second power transmission part including a connected part in a horizontal direction from the first power transmission part in the adapter die, and a third power transmission part connected to the second power transmission region in the vertical direction from the second power transmission part. A voltage conversion circuit is arranged on the first power transmission path.

Abstract: Provided is a processor configured to compute elements affecting an optimization matrix in connection with a first measurement, among elements of a Hessian matrix, instead of generating a whole Hessian matrix for a map point and a camera pose based on all measurements, and accumulate the computed elements over the optimization matrix used to perform optimization operations in relation to states of the map point and the camera pose.