PROGRESSIVE NEURAL NETWORKS

• Main Authors: RUSU, ANDREI-ALEXANDRU, PASCANU, RAZVAN, HADSELL, RAIA THAIS, DESJARDINS, GUILLAUME, SOYER, HUBERT JOSEF, KAVUKCUOGLU, KORAY, KIRKPATRICK, JAMES, RABINOWITZ, NEIL CHARLES
• Format: Patent
• Language: English; Polish
• Published: 13.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.