CA2901596A1 - Methodes et systemes de realisation d'apprentissage de renforcement dans les environnements hierarchiques et etendus temporairement - Google Patents

Methodes et systemes de realisation d'apprentissage de renforcement dans les environnements hierarchiques et etendus temporairement Download PDF

Info

Publication number
CA2901596A1
CA2901596A1 CA2901596A CA2901596A CA2901596A1 CA 2901596 A1 CA2901596 A1 CA 2901596A1 CA 2901596 A CA2901596 A CA 2901596A CA 2901596 A CA2901596 A CA 2901596A CA 2901596 A1 CA2901596 A1 CA 2901596A1
Authority
CA
Canada
Prior art keywords
module
output
action
state
weighted
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CA2901596A
Other languages
English (en)
Inventor
Daniel H. Rasmussn
Christopher D. Eliasmith
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Applied Brain Research Inc
Original Assignee
Applied Brain Research Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Applied Brain Research Inc filed Critical Applied Brain Research Inc
Priority to CA2901596A priority Critical patent/CA2901596A1/fr
Publication of CA2901596A1 publication Critical patent/CA2901596A1/fr
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
CA2901596A 2015-08-26 2015-08-26 Methodes et systemes de realisation d'apprentissage de renforcement dans les environnements hierarchiques et etendus temporairement Pending CA2901596A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CA2901596A CA2901596A1 (fr) 2015-08-26 2015-08-26 Methodes et systemes de realisation d'apprentissage de renforcement dans les environnements hierarchiques et etendus temporairement

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CA2901596A CA2901596A1 (fr) 2015-08-26 2015-08-26 Methodes et systemes de realisation d'apprentissage de renforcement dans les environnements hierarchiques et etendus temporairement

Publications (1)

Publication Number Publication Date
CA2901596A1 true CA2901596A1 (fr) 2017-02-26

Family

ID=58185877

Family Applications (1)

Application Number Title Priority Date Filing Date
CA2901596A Pending CA2901596A1 (fr) 2015-08-26 2015-08-26 Methodes et systemes de realisation d'apprentissage de renforcement dans les environnements hierarchiques et etendus temporairement

Country Status (1)

Country Link
CA (1) CA2901596A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112771542A (zh) * 2018-09-27 2021-05-07 渊慧科技有限公司 以学习的视觉实体为基础的强化学习神经网络

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112771542A (zh) * 2018-09-27 2021-05-07 渊慧科技有限公司 以学习的视觉实体为基础的强化学习神经网络
CN112771542B (zh) * 2018-09-27 2024-03-05 渊慧科技有限公司 以学习的视觉实体为基础的强化学习神经网络

Similar Documents

Publication Publication Date Title
EP3136304A1 (fr) Procédés et systèmes pour effectuer l'apprentissage par renforcement dans des environnements hiérarchiques et prolongés dans la durée
US10671912B2 (en) Spatio-temporal spiking neural networks in neuromorphic hardware systems
CN107077637B (zh) 神经网络中的差分编码
Maass et al. On the computational power of circuits of spiking neurons
Li et al. Finite-time synchronization of fractional-order memristive recurrent neural networks with discontinuous activation functions
Hochreiter et al. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies
US9460385B2 (en) Apparatus and methods for rate-modulated plasticity in a neuron network
US10970626B2 (en) Multi-memristive synapse with clock-arbitrated weight update
CN110428042B (zh) 往复地缩放神经元的连接权重和输入值来挫败硬件限制
Zhou et al. Discrete-time recurrent neural networks with complex-valued linear threshold neurons
KR20160136364A (ko) 콜드 뉴런 스파이크 타이밍 역 전파
US10552734B2 (en) Dynamic spatial target selection
US11562249B2 (en) DNN training with asymmetric RPU devices
KR20160084401A (ko) 스파이킹 뉴럴 네트워크들에서 리플레이를 사용한 시냅스 학습의 구현
WO2022253229A1 (fr) Procédé d'entraînement de poids synaptique, procédé de reconnaissance de cible, dispositif électronique et support
Katte Recurrent neural network and its various architecture types
EP3685318A1 (fr) Regroupement temporel et corrélation dans un réseau neuronal artificiel
KR20160124791A (ko) 좌표 변환을 위한 위상 코딩
Koprinkova‐Hristova et al. Heuristic dynamic programming using echo state network as online trainable adaptive critic
WO2020240288A1 (fr) Gestion de bruit et de signal pour matrice de rpu
CN113537455B (zh) 突触权重训练方法、电子设备和计算机可读介质
US20230351195A1 (en) Neurosynaptic Processing Core with Spike Time Dependent Plasticity (STDP) Learning For a Spiking Neural Network
CA2901596A1 (fr) Methodes et systemes de realisation d'apprentissage de renforcement dans les environnements hierarchiques et etendus temporairement
CN113269313B (zh) 突触权重训练方法、电子设备和计算机可读介质
Licata Are neural networks imitations of mind

Legal Events

Date Code Title Description
EEER Examination request

Effective date: 20200820

EEER Examination request

Effective date: 20200820

EEER Examination request

Effective date: 20200820

EEER Examination request

Effective date: 20200820

EEER Examination request

Effective date: 20200820

EEER Examination request

Effective date: 20200820

EEER Examination request

Effective date: 20200820