Abstract: Systems and methods for inverse rendering training for chart code generation can include obtaining input data including at least a portion of seed language and processing the input data with a first machine-learned code generation model to generate, as output of the machine-learned model, synthesized language. The systems and methods can process, using a parser, the synthesized language to generate a training pair including a programmatically rendered graphic and the synthesized language. The systems and methods can include training a second code generation model to perform inverse rendering on the training pair, wherein training the second code generation model to perform inverse rendering on the training pair includes training the second code generation model to generate the synthesized language when given the programmatically rendered graphic.

Abstract: A system including a multi-layer analog neural network that has a single layer of physical analog neurons that is re-usable for implementing a plurality of layers of the multi-layer analog neural network. Each of the physical analog neurons is configured to receive a neuron input and to process the neuron input to generate a neuron output that is fed as input to all physical analog neurons of the single layer, and each of the physical analog neurons includes a respective weight memory. The system controller is operable to obtain, for each physical analog neuron, a respective set of neuron weight vectors with each neuron weight vector corresponding to a respective layer of the plurality of layers of the multi-layer analog neural network; store, for each physical analog neuron, the respective set of neuron weights in the respective weight memory of the physical analog neuron.

Abstract: A computer-implemented method for compensation of errors due to fabrication tolerance in an analog neural network is described. The method includes: receiving a set of input weights from a trained digital neural network, the digital neural network having the same architecture as the analog neural network and being trained in a digital environment without errors due to fabrication tolerance; loading the set of input weights to the analog neural network; receiving (i) a set of test inputs for error compensation, and (ii) a set of expected outputs that is obtained by processing the set of test inputs using the trained digital neural network; processing the set of test inputs using the analog neural network to generate a set of test outputs; processing the set of test outputs and the set of expected outputs to generate a set of updated weights for the analog neural network; and loading the set of updated weights to the analog neural network.

Abstract: An apparatus includes an analog neural network, a digital controller and a memory device. The analog neural network can include a first layer having a plurality of neurons. The plurality of neurons can be reused to form a second layer of the analog neural network. Each neuron can have a plurality of inputs. The digital controller can be coupled to the analog neural network, and can provide a weight for each input of the plurality of inputs. The memory device can be coupled to the digital controller to store the weight for each input of the plurality of inputs.

Abstract: A system including a multi-layer analog neural network that has a single layer of physical analog neurons that is re-usable for implementing a plurality of layers of the multi-layer analog neural network. Each of the physical analog neurons is configured to receive a neuron input and to process the neuron input to generate a neuron output that is fed as input to all physical analog neurons of the single layer, and each of the physical analog neurons includes a respective weight memory. The system controller is operable to obtain, for each physical analog neuron, a respective set of neuron weight vectors with each neuron weight vector corresponding to a respective layer of the plurality of layers of the multi-layer analog neural network; store, for each physical analog neuron, the respective set of neuron weights in the respective weight memory of the physical analog neuron.