Inait Sa

Ecole Polytechnique Federale De Lausanne

Societe Des Produits Nestle S.a.

Nestec S.a.

Henry Markram

Kathryn Pamela Hess Bellwald

John Rahmon

Felix Schürmann

Fabien Jonathan Delalondre

Ran Levi

Felix Schuermann

Daniel Milan Lütgehetmann

Constantin Cosmin Atanasoaei

Eilif Benjamin Muller

Rodrigo De Campos Perin

Thomas K Berger

Johannes Le Coutre

Susana Camacho

Maurizio Pezzoli

James Gonzalo King

Stephanie Michlig Gonzalez

Csaba Erö

Willem Wybo

Sean Lewis Hill

Marc-Oliver Gewaltig

Christian Pozzorini

Kathryn Hess

Idan Segev

Michael Wolfgang Reimann

Wulfram Gerstner

Christian Rössert

Michele De Gruttola

Max Christian Nolte

Stephanie Michlig Gonzales

Stéphanie Michlig Gonzalez

Methods, systems, and devices for homomorphic encryption. In one implementation, the methods include inputting first data into a recurrent artificial neural network, identifying patterns of activity in the recurrent artificial neural network that are responsive to the input of the secure data, storing second data representing whether the identified patterns of activity comports with topological patterns, and statistically analyzing the second data to draw conclusions about the first data.

Homomorphic encryption

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for characterizing activity in a recurrent artificial neural network. In one aspect, a method includes outputting digits from a recurrent artificial neural network, wherein each digit represents whether or not activity within a particular group of nodes in the recurrent artificial neural network comports with a respective pattern of activity.

Characterizing activity in a recurrent artificial neural network

A method includes defining a plurality of different windows of time in a recurrent artificial neural network, wherein each of the different windows has different durations, has different start times, or has both different durations and different start times, identifying occurrences of topological patterns of activity in the recurrent artificial neural network in the different windows of time, comparing the occurrences of the topological patterns of activity in the different windows, and classifying, based on a result of the comparison, a first decision that is represented by a first topological pattern of activity that occurs in a first of the windows as less robust than a second decision that is represented by a second topological pattern of activity that occurs in a second of the windows.

Interpreting and improving the processing results of recurrent neural networks

Abstracting data that originates from different sensors and transducers using artificial neural networks. A method can include identifying topological patterns of activity in a recurrent artificial neural network and outputting a collection of digits. The topological patterns are responsive to an input, into the recurrent artificial neural network, of first data originating from a first sensor and second data originating from a second sensor. Each topological pattern abstracts a characteristic shared by the first data and the second data. The first and second sensors sense different data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.

Input into a neural network

Distance metrics and clustering in recurrent neural networks. For example, a method includes determining whether topological patterns of activity in a collection of topological patterns occur in a recurrent artificial neural network in response to input of first data into the recurrent artificial neural network, and determining a distance between the first data and either second data or a reference based on the topological patterns of activity that are determined to occur in response to the input of the first data.

Distance metrics and clustering in recurrent neural networks

Methods, systems, and devices for encrypting and decrypting data. In one implementation, an encryption method includes inputting plaintext into a recurrent artificial neural network, identifying topological structures in patterns of activity in the recurrent artificial neural network, wherein the patterns of activity are responsive to the input of the plaintext, representing the identified topological structures in a binary sequence of length L and implementing a permutation of the set of all binary codewords of length L. The implemented permutation is a function from the set of binary codewords of length L to itself that is injective and surjective.

Encrypting and decrypting information

The simplification of neural network models is described. For example, a method for simplifying a neural network model includes providing the neural network model to be simplified, defining a first temporal filter for the conveyance of input from a neuron to an other spatially-extended neuron along the arborized projection, defining a second temporal filter for the conveyance of input from yet another neuron to the spatially-extended neuron along the arborized projection, replacing, in the neural network model, the first, spatially-extended neuron with a first, spatially-constrained neuron and the arborized projection with a first connection extending between the first, spatially-constrained neuron and the second neuron, wherein the first connection filters input from the second neuron in accordance with the first temporal filter and a second connection extending between the first spatially-constrained neuron and the third neuron.

Simplification of spiking neural network models

A method that is implemented by one or more data processing devices can include receiving a training set that includes a plurality of representations of topological structures in patterns of activity in a source neural network and training a neural network using the representations either as an input to the neural network or as a target answer vector. The activity is responsive to an input into the source neural network.

Encoding and decoding information

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for organizing trained and untrained neural networks. In one aspect, a neural network device includes a collection of node assemblies interconnected by between-assembly links, each node assembly itself comprising a network of nodes interconnected by a plurality of within-assembly links, wherein each of the between-assembly links and the within-assembly links have an associated weight, each weight embodying a strength of connection between the nodes joined by the associated link, the nodes within each assembly being more likely to be connected to other nodes within that assembly than to be connected to nodes within others of the node assemblies.

Organizing neural networks

In one implementation, a method is implemented by a neural network device and includes inputting a representation of topological structures in patterns of activity in a source neural network, wherein the activity is responsive to an input into the source neural network, processing the representation, and outputting a result of the processing of the representation. The processing is consistent with a training of the neural network to process different such representations of topological structures in patterns of activity in the source neural network.

Encoding and decoding information and artificial neural networks

Application of the output from a recurrent artificial neural network to a variety of different applications. A method can include identifying topological patterns of activity in a recurrent artificial neural network, outputting a collection of digits, and inputting a first digit of the collection to a first application that is designed to fulfil a first purpose and to a second application that is designed to fulfil a second purpose, wherein the first purpose differs from the second purpose. The topological patterns are responsive to an input of data into the recurrent artificial neural network and each topological pattern abstracts a characteristic of the input data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.

Output from a recurrent neural network

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reconstructing and simulating neocortical microcircuitry. In one aspect, a method includes providing a model of neural tissue, the model including different types of neural cells and dynamic synaptic interconnections between the neural cells, changing a parameter in the model; and identifying a change in a computational state of the model of the neural tissue responsive to the change in the parameter. The change in the parameter can, e.g., change behavior of neural cells of at least one type, change interconnectivity between neural cells, or target a location within a volume in the model that interacts with multiple types of neural cells.

Reconstruction and simulation of neocortical microcircuitry

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for characterizing activity in a recurrent artificial neural network. In one aspect, a method for identifying decision moments in a recurrent artificial neural network includes determining a complexity of patterns of activity in the recurrent artificial neural network, wherein the activity is responsive to input into the recurrent artificial neural network, determining a timing of activity having a complexity that is distinguishable from other activity that is responsive to the input, and identifying the decision moment based on the timing of the activity that has the distinguishable complexity.

Growing community of inventors

Lausanne, Switzerland

Henry Markram