Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

• URL: http://arxiv.org/abs/2006.12878v2
• Date: Fri, 11 Dec 2020 14:31:35 GMT
• Title: Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
• Authors: Julien Launay, Iacopo Poli, Fran\c{c}ois Boniface, Florent Krzakala
• Abstract summary: We study the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing. Our findings show that it successfully trains a large range of state-of-the-art deep learning architectures, with performance close to fine-tuned backpropagation.
• Score: 22.438735897480417
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the training process. Furthermore, its biological plausibility is being challenged. Alternative schemes have been devised; yet, under the constraint of synaptic asymmetry, none have scaled to modern deep learning tasks and architectures. Here, we challenge this perspective, and study the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing. In contrast with previous studies limited to computer vision tasks, our findings show that it successfully trains a large range of state-of-the-art deep learning architectures, with performance close to fine-tuned backpropagation. At variance with common beliefs, our work supports that challenging tasks can be tackled in the absence of weight transport.

Related papers

• Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning [17.299267108673277]
  Hebbian learning is a biological principle that intuitively describes how neurons adapt their connections through repeated stimuli.<n>We introduce the Structural Projection Hebbian Representation (SPHeRe), a novel unsupervised learning method.<n> Experimental results show that SPHeRe achieves SOTA performance among unsupervised synaptic plasticity approaches.
  arXiv  Detail & Related papers  (2025-10-16T15:47:29Z)
• The Importance of Being Lazy: Scaling Limits of Continual Learning [60.97756735877614]
  We show that increasing model width is only beneficial when it reduces the amount of feature learning, yielding more laziness.<n>We study the intricate relationship between feature learning, task non-stationarity, and forgetting, finding that high feature learning is only beneficial with highly similar tasks.
  arXiv  Detail & Related papers  (2025-06-20T10:12:38Z)
• Recurrent Joint Embedding Predictive Architecture with Recurrent Forward Propagation Learning [0.0]
  We introduce a vision network inspired by biological principles. The network learns by predicting the representation of the next image patch (fixation) based on the sequence of past fixations. We also introduce emphRecurrent-Forward propagation, a learning algorithm that avoids biologically unrealistic backpropagation through time or memory-inefficient real-time recurrent learning.
  arXiv  Detail & Related papers  (2024-11-10T01:40:42Z)
• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales [54.78115855552886]
  We show how to construct over-complete invariants with a Convolutional Neural Networks (CNN)-like hierarchical architecture. With the over-completeness, discriminative features w.r.t. the task can be adaptively formed in a Neural Architecture Search (NAS)-like manner. For robust and interpretable vision tasks at larger scales, hierarchical invariant representation can be considered as an effective alternative to traditional CNN and invariants.
  arXiv  Detail & Related papers  (2024-02-23T16:50:07Z)
• Training Neural Networks with Internal State, Unconstrained Connectivity, and Discrete Activations [66.53734987585244]
  True intelligence may require the ability of a machine learning model to manage internal state. We show that we have not yet discovered the most effective algorithms for training such models. We present one attempt to design such a training algorithm, applied to an architecture with binary activations and only a single matrix of weights.
  arXiv  Detail & Related papers  (2023-12-22T01:19:08Z)
• Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning [1.9580473532948401]
  We introduce a novel neural network architecture inspired by neuromodulation in biological nervous systems. We show that this approach has strong learning performance per task despite the very small number of learnable parameters.
  arXiv  Detail & Related papers  (2022-04-08T21:12:13Z)
• Towards Scaling Difference Target Propagation by Learning Backprop Targets [64.90165892557776]
  Difference Target Propagation is a biologically-plausible learning algorithm with close relation with Gauss-Newton (GN) optimization. We propose a novel feedback weight training scheme that ensures both that DTP approximates BP and that layer-wise feedback weight training can be restored. We report the best performance ever achieved by DTP on CIFAR-10 and ImageNet.
  arXiv  Detail & Related papers  (2022-01-31T18:20:43Z)
• Heuristic Search Planning with Deep Neural Networks using Imitation, Attention and Curriculum Learning [1.0323063834827413]
  This paper presents a network model to learn a capable of relating relating to distant parts of the state space via optimal plan imitation. To counter the limitation of the method in the creation of problems of increasing difficulty, we demonstrate the use of curriculum learning, where newly solved problem instances are added to the training set.
  arXiv  Detail & Related papers  (2021-12-03T14:01:16Z)
• Learning to Learn with Feedback and Local Plasticity [9.51828574518325]
  We employ meta-learning to discover networks that learn using feedback connections and local, biologically inspired learning rules. Our experiments show that meta-trained networks effectively use feedback connections to perform online credit assignment in multi-layer architectures.
  arXiv  Detail & Related papers  (2020-06-16T22:49:07Z)
• Learning to Stop While Learning to Predict [85.7136203122784]
  Many algorithm-inspired deep models are restricted to a fixed-depth'' for all inputs. Similar to algorithms, the optimal depth of a deep architecture may be different for different input instances. In this paper, we tackle this varying depth problem using a steerable architecture. We show that the learned deep model along with the stopping policy improves the performances on a diverse set of tasks.
  arXiv  Detail & Related papers  (2020-06-09T07:22:01Z)
• Structure preserving deep learning [1.2263454117570958]
  deep learning has risen to the foreground as a topic of massive interest. There are multiple challenging mathematical problems involved in applying deep learning. A growing effort to mathematically understand the structure in existing deep learning methods.
  arXiv  Detail & Related papers  (2020-06-05T10:59:09Z)
• Neural Topological SLAM for Visual Navigation [112.73876869904]
  We design topological representations for space that leverage semantics and afford approximate geometric reasoning. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation.
  arXiv  Detail & Related papers  (2020-05-25T17:56:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.