US 12,242,784 B1
Method, product, and system for a sequence generation ecosystem using machine learning
Shadi Saba, San Jose, CA (US); Roque Alejandro Arcudia Hernandez, San Jose, CA (US); Uyen Huynh Ha Nguyen, San Jose, CA (US); Pedro Eugênio Rocha Medeiros, Serra-Belo Horizone/MG (BR); and Claire Liyan Ying, Los Altos Hills, CA (US)
Assigned to Cadence Design Systems, Inc., San Jose, CA (US)
Filed by Cadence Design Systems, Inc., San Jose, CA (US)
Filed on Sep. 30, 2021, as Appl. No. 17/490,378.
Int. Cl. G06F 30/333 (2020.01); G06N 5/022 (2023.01)
CPC G06F 30/333 (2020.01) [G06N 5/022 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing system, comprising:
memory having a set of instructions; and
a processor that executes the set of instructions to implement an electronic design system, the electronic design system being for identifying one or more transitions for a respective design under test, the electronic design system comprising:
a machine learning exploration unit that selects and simulates one or more actions on a design under test at the machine learning exploration unit at least by:
processing state information using a respective machine learning model that outputs a selection of at least one action, the state information representing a then current state of the design under test in a simulator,
applying the selected at least one action to the design under test in the simulator, and
outputting state transition data corresponding to a change in the design under test from the then current state to a different state; and
a state space manager that maintains state transition data, wherein the state space manager receives state transition data from the machine learning exploration unit and merges the state transition data into a state space representation.