Authors

* External authors

Venue

Date

Share

A Discussion about Explainable Inference on Sequential Data via Memory-Tracking

Biagio La Rosa*

Roberto Capobianco

Daniele Nardi*

* External authors

AIxIA 2021

2021

Abstract

The recent explosion of deep learning techniques boosted the application of Artificial Intelligence in a variety of domains, thanks to their high performance. However, performance comes at the cost of interpretability: deep models contain hundred of nested non-linear operations that make it impossible to keep track of the chain of steps that bring to a given answer. In our recently published paper [10], we propose a method to improve the interpretability of a class of deep models, namely Memory Augmented Neural Networks (MANNs), when dealing with sequential data. Exploiting the capability of MANNs to store and access data in external memory, tracking the process, and connecting this information to the input sequence, our method extracts the most relevant sub-sequences that explain the answer. We evaluate our approach both on a modified T-maze [3, 25] and on the Story Cloze Test [15], obtaining promising results.

Related Publications

Real-time Trajectory Generation via Dynamic Movement Primitives for Autonomous Racing

ACC, 2024
Catherine Weaver*, Roberto Capobianco, Peter R. Wurman, Peter Stone, Masayoshi Tomizuka*

We employ sequences of high-order motion primitives for efficient online trajectory planning, enabling competitive racecar control even when the car deviates from an offline demonstration. Dynamic Movement Primitives (DMPs) utilize a target-driven non-linear differential equ…

Towards a fuller understanding of neurons with Clustered Compositional Explanations

NeurIPS, 2023
Biagio La Rosa*, Leilani H. Gilpin*, Roberto Capobianco

Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations used to check the alignment (i.e., the highest ones), thus lacking c…

Memory Replay For Continual Learning With Spiking Neural Networks

IEEE MSLP, 2023
Michela Proietti*, Alessio Ragno*, Roberto Capobianco

Two of the most impressive features of biological neural networks are their high energy efficiency and their ability to continuously adapt to varying inputs. On the contrary, the amount of power required to train top-performing deep learning models rises as they become more …

  • HOME
  • Publications
  • A Discussion about Explainable Inference on Sequential Data via Memory-Tracking

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.