Recursive Sketches for Modular Deep Learning
arXiv:1905.12730
Abstract
We present a mechanism to compute a sketch (succinct summary) of how a complex modular deep network processes its inputs. The sketch summarizes essential information about the inputs and outputs of the network and can be used to quickly identify key components and summary statistics of the inputs. Furthermore, the sketch is recursive and can be unrolled to identify sub-components of these components and so forth, capturing a potentially complicated DAG structure. These sketches erase gracefully; even if we erase a fraction of the sketch at random, the remainder still retains the `high-weight' information present in the original sketch. The sketches can also be organized in a repository to implicitly form a `knowledge graph'; it is possible to quickly retrieve sketches in the repository that are related to a sketch of interest; arranged in this fashion, the sketches can also be used to learn emerging concepts by looking for new clusters in sketch space. Finally, in the scenario where we want to learn a ground truth deep network, we show that augmenting input/output pairs with these sketches can theoretically make it easier to do so.
arXiv commentPublished in ICML 2019
References in corpus (15)
- Distilling the Knowledge in a Neural Network
- End-To-End Memory Networks
- PathNet: Evolution Channels Gradient Descent in Super Neural Networks
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
- Convergence Analysis of Two-layer Neural Networks with ReLU Activation
- Provable Bounds for Learning Some Deep Representations
- Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
- Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience
- Learning to Transduce with Unbounded Memory
- Recovery Guarantees for One-hidden-layer Neural Networks
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
- Reinforcement Learning Neural Turing Machines - Revised
- Associative Long Short-Term Memory
- When is a Convolutional Filter Easy To Learn?
- Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels