Memory Accelerator

Memory accelerators aim to drastically improve the energy efficiency and speed of deep neural network (DNN) inference by performing computations directly within the memory array, minimizing data movement. Current research focuses on optimizing various DNN architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers, for in-memory computing using techniques like ternary weight quantization and hardware-aware training. This approach holds significant promise for reducing the power consumption and latency of AI applications, particularly in resource-constrained environments like edge devices and IoT systems.