home.social

#rnns — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #rnns, aggregated by home.social.

  1. 🧠 New paper by Deistler et al: #JAXLEY: differentiable #simulation for large-scale training of detailed #biophysical #models of #NeuralDynamics.

    They present a #differentiable #GPU accelerated #simulator that trains #morphologically detailed biophysical #neuron models with #GradientDescent. JAXLEY fits intracellular #voltage and #calcium data, scales to 1000s of compartments, trains biophys. #RNNs on #WorkingMemory tasks & even solves #MNIST.

    🌍 doi.org/10.1038/s41592-025-028

    #Neuroscience #CompNeuro

  2. 🧠 New paper by Deistler et al: #JAXLEY: differentiable #simulation for large-scale training of detailed #biophysical #models of #NeuralDynamics.

    They present a #differentiable #GPU accelerated #simulator that trains #morphologically detailed biophysical #neuron models with #GradientDescent. JAXLEY fits intracellular #voltage and #calcium data, scales to 1000s of compartments, trains biophys. #RNNs on #WorkingMemory tasks & even solves #MNIST.

    🌍 doi.org/10.1038/s41592-025-028

    #Neuroscience #CompNeuro

  3. 🧠 New paper by Deistler et al: #JAXLEY: differentiable #simulation for large-scale training of detailed #biophysical #models of #NeuralDynamics.

    They present a #differentiable #GPU accelerated #simulator that trains #morphologically detailed biophysical #neuron models with #GradientDescent. JAXLEY fits intracellular #voltage and #calcium data, scales to 1000s of compartments, trains biophys. #RNNs on #WorkingMemory tasks & even solves #MNIST.

    🌍 doi.org/10.1038/s41592-025-028

    #Neuroscience #CompNeuro

  4. 🧠 New paper by Deistler et al: #JAXLEY: differentiable #simulation for large-scale training of detailed #biophysical #models of #NeuralDynamics.

    They present a #differentiable #GPU accelerated #simulator that trains #morphologically detailed biophysical #neuron models with #GradientDescent. JAXLEY fits intracellular #voltage and #calcium data, scales to 1000s of compartments, trains biophys. #RNNs on #WorkingMemory tasks & even solves #MNIST.

    🌍 doi.org/10.1038/s41592-025-028

    #Neuroscience #CompNeuro

  5. 🧠 New paper by Deistler et al: #JAXLEY: differentiable #simulation for large-scale training of detailed #biophysical #models of #NeuralDynamics.

    They present a #differentiable #GPU accelerated #simulator that trains #morphologically detailed biophysical #neuron models with #GradientDescent. JAXLEY fits intracellular #voltage and #calcium data, scales to 1000s of compartments, trains biophys. #RNNs on #WorkingMemory tasks & even solves #MNIST.

    🌍 doi.org/10.1038/s41592-025-028

    #Neuroscience #CompNeuro

  6. 🧠 New preprint by Codol et al. (2025): Brain-like #NeuralDynamics for #behavioral control develop through #ReinforcementLearning. They show that only #RL, not #SupervisedLearning, yields neural activity geometries & dynamics matching monkey #MotorCortex recordings. RL-trained #RNNs operate at the edge of #chaos, reproduce adaptive reorganization under #visuomotor rotation, and require realistic limb #biomechanics to achieve brain-like control.

    🌍 doi.org/10.1101/2024.10.04.616

    #CompNeuro #Neuroscience

  7. 🧠 New preprint by Codol et al. (2025): Brain-like #NeuralDynamics for #behavioral control develop through #ReinforcementLearning. They show that only #RL, not #SupervisedLearning, yields neural activity geometries & dynamics matching monkey #MotorCortex recordings. RL-trained #RNNs operate at the edge of #chaos, reproduce adaptive reorganization under #visuomotor rotation, and require realistic limb #biomechanics to achieve brain-like control.

    🌍 doi.org/10.1101/2024.10.04.616

    #CompNeuro #Neuroscience

  8. 🧠 New preprint by Codol et al. (2025): Brain-like #NeuralDynamics for #behavioral control develop through #ReinforcementLearning. They show that only #RL, not #SupervisedLearning, yields neural activity geometries & dynamics matching monkey #MotorCortex recordings. RL-trained #RNNs operate at the edge of #chaos, reproduce adaptive reorganization under #visuomotor rotation, and require realistic limb #biomechanics to achieve brain-like control.

    🌍 doi.org/10.1101/2024.10.04.616

    #CompNeuro #Neuroscience

  9. 🧠 New preprint by Codol et al. (2025): Brain-like #NeuralDynamics for #behavioral control develop through #ReinforcementLearning. They show that only #RL, not #SupervisedLearning, yields neural activity geometries & dynamics matching monkey #MotorCortex recordings. RL-trained #RNNs operate at the edge of #chaos, reproduce adaptive reorganization under #visuomotor rotation, and require realistic limb #biomechanics to achieve brain-like control.

    🌍 doi.org/10.1101/2024.10.04.616

    #CompNeuro #Neuroscience

  10. 🧠 New preprint by Codol et al. (2025): Brain-like #NeuralDynamics for #behavioral control develop through #ReinforcementLearning. They show that only #RL, not #SupervisedLearning, yields neural activity geometries & dynamics matching monkey #MotorCortex recordings. RL-trained #RNNs operate at the edge of #chaos, reproduce adaptive reorganization under #visuomotor rotation, and require realistic limb #biomechanics to achieve brain-like control.

    🌍 doi.org/10.1101/2024.10.04.616

    #CompNeuro #Neuroscience

  11. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  12. : The models having sequential data as input or output are called .

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks () and Long Short-Term Memory() are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  13. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  14. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  15. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  16. Showing my love for RNNs and functional programming by implementing Mamba2 with Elixir. Wish me luck! #Elixir #LLMs #functionalprogramming #rnns

  17. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  18. : The models having sequential data as input or output are called .

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks () and Long Short-Term Memory() are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  19. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  20. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  21. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  22. Learning better with Dale’s Law: A Spectral Perspective - #NeurIPS2023 contribution by Li et al. (2023). It discusses how to train brainlike #RNNs with separate inhibitory and excitatory units with similar performance as standard RNNs:

    🌍 openreview.net/forum?id=rDiMgZ

    #RNN #DalesLaw #CompNeuro #Neuroscience

  23. Learning better with Dale’s Law: A Spectral Perspective - #NeurIPS2023 contribution by Li et al. (2023). It discusses how to train brainlike #RNNs with separate inhibitory and excitatory units with similar performance as standard RNNs:

    🌍 openreview.net/forum?id=rDiMgZ

    #RNN #DalesLaw #CompNeuro #Neuroscience

  24. Learning better with Dale’s Law: A Spectral Perspective - #NeurIPS2023 contribution by Li et al. (2023). It discusses how to train brainlike #RNNs with separate inhibitory and excitatory units with similar performance as standard RNNs:

    🌍 openreview.net/forum?id=rDiMgZ

    #RNN #DalesLaw #CompNeuro #Neuroscience

  25. Learning better with Dale’s Law: A Spectral Perspective - #NeurIPS2023 contribution by Li et al. (2023). It discusses how to train brainlike #RNNs with separate inhibitory and excitatory units with similar performance as standard RNNs:

    🌍 openreview.net/forum?id=rDiMgZ

    #RNN #DalesLaw #CompNeuro #Neuroscience

  26. Learning better with Dale’s Law: A Spectral Perspective - #NeurIPS2023 contribution by Li et al. (2023). It discusses how to train brainlike #RNNs with separate inhibitory and excitatory units with similar performance as standard RNNs:

    🌍 openreview.net/forum?id=rDiMgZ

    #RNN #DalesLaw #CompNeuro #Neuroscience

  27. 1997 with the advent of Long Short-Term Memory recurrent #neuralnetworks marks the subsequent step in our brief history of )large) #languagemodels from last week's #ise2023 lecture. Introduced by Sepp Hochreiter and Jürgen Schmidhuber #LSTM #RNNs enabled efficient processing of sequences of data.
    Slides: drive.google.com/file/d/1atNvM
    #nlp #llm #llms #ai #artificialintelligence #lecture @fizise

  28. 1997 with the advent of Long Short-Term Memory recurrent #neuralnetworks marks the subsequent step in our brief history of )large) #languagemodels from last week's #ise2023 lecture. Introduced by Sepp Hochreiter and Jürgen Schmidhuber #LSTM #RNNs enabled efficient processing of sequences of data.
    Slides: drive.google.com/file/d/1atNvM
    #nlp #llm #llms #ai #artificialintelligence #lecture @fizise

  29. 1997 with the advent of Long Short-Term Memory recurrent #neuralnetworks marks the subsequent step in our brief history of )large) #languagemodels from last week's #ise2023 lecture. Introduced by Sepp Hochreiter and Jürgen Schmidhuber #LSTM #RNNs enabled efficient processing of sequences of data.
    Slides: drive.google.com/file/d/1atNvM
    #nlp #llm #llms #ai #artificialintelligence #lecture @fizise

  30. 1997 with the advent of Long Short-Term Memory recurrent #neuralnetworks marks the subsequent step in our brief history of )large) #languagemodels from last week's #ise2023 lecture. Introduced by Sepp Hochreiter and Jürgen Schmidhuber #LSTM #RNNs enabled efficient processing of sequences of data.
    Slides: drive.google.com/file/d/1atNvM
    #nlp #llm #llms #ai #artificialintelligence #lecture @fizise

  31. 1997 with the advent of Long Short-Term Memory recurrent #neuralnetworks marks the subsequent step in our brief history of )large) #languagemodels from last week's #ise2023 lecture. Introduced by Sepp Hochreiter and Jürgen Schmidhuber #LSTM #RNNs enabled efficient processing of sequences of data.
    Slides: drive.google.com/file/d/1atNvM
    #nlp #llm #llms #ai #artificialintelligence #lecture @fizise

  32. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  33. : The models having sequential data as input or output are called .

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks () and Long Short-Term Memory() are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  34. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  35. #ITByte: The #MachineLearning models having sequential data as input or output are called #SequenceModels.

    It includes text streams, video clips, audio clips, time-series data, etc. Recurrent Neural Networks (#RNNs) and Long Short-Term Memory(#LSTM) are popular algorithms used in sequence models.

    knowledgezone.co.in/trends/exp

  36. 'Minimal Width for Universal Property of Deep RNN', by Chang hoon Song, Geonho Hwang, Jun ho Lee, Myungjoo Kang.

    jmlr.org/papers/v24/22-1191.ht

    #rnns #rnn #deep

  37. 'Minimal Width for Universal Property of Deep RNN', by Chang hoon Song, Geonho Hwang, Jun ho Lee, Myungjoo Kang.

    jmlr.org/papers/v24/22-1191.ht

    #rnns #rnn #deep

  38. 'Minimal Width for Universal Property of Deep RNN', by Chang hoon Song, Geonho Hwang, Jun ho Lee, Myungjoo Kang.

    jmlr.org/papers/v24/22-1191.ht

    #rnns #rnn #deep

  39. 'Minimal Width for Universal Property of Deep RNN', by Chang hoon Song, Geonho Hwang, Jun ho Lee, Myungjoo Kang.

    jmlr.org/papers/v24/22-1191.ht

    #rnns #rnn #deep

  40. 'Minimal Width for Universal Property of Deep RNN', by Chang hoon Song, Geonho Hwang, Jun ho Lee, Myungjoo Kang.

    jmlr.org/papers/v24/22-1191.ht

    #rnns #rnn #deep

  41. Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning

    Matthew Kyle Schlegel, Volodymyr Tkachuk, Adam M White, Martha White

    openreview.net/forum?id=K6g4Mb

    #rnns #rnn #reinforcement

  42. Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning

    Matthew Kyle Schlegel, Volodymyr Tkachuk, Adam M White, Martha White

    openreview.net/forum?id=K6g4Mb

    #rnns #rnn #reinforcement

  43. Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning

    Matthew Kyle Schlegel, Volodymyr Tkachuk, Adam M White, Martha White

    openreview.net/forum?id=K6g4Mb

    #rnns #rnn #reinforcement

  44. Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning

    Matthew Kyle Schlegel, Volodymyr Tkachuk, Adam M White, Martha White

    openreview.net/forum?id=K6g4Mb

    #rnns #rnn #reinforcement

  45. Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning

    Matthew Kyle Schlegel, Volodymyr Tkachuk, Adam M White, Martha White

    openreview.net/forum?id=K6g4Mb

    #rnns #rnn #reinforcement