fbpx
Opening The Black Box—Interpretability In Deep Learning Opening The Black Box—Interpretability In Deep Learning
Editor’s Note: See Joris and Matteo at their tutorial “Opening The Black Box — Interpretability in Deep Learning” at ODSC Europe 2019 this November... Opening The Black Box—Interpretability In Deep Learning

Editor’s Note: See Joris and Matteo at their tutorial Opening The Black Box — Interpretability in Deep Learningat ODSC Europe 2019 this November 20th in London.

Why interpretability? 

In the last decade, the application of deep neural networks to long-standing problems has brought a breakthrough in performance and prediction power. However, high accuracy, deriving from the increased model complexity, often comes at the price of loss of interpretability, i.e., many of these models behave as black-boxes and fail to provide explanations on their predictions. While in certain application fields this issue may play a secondary role, in high-risk domains, e.g., health care, it is crucial to build trust in a model and being able to understand its behavior. 

[Related Article: Cracking the Box: Interpreting Black Box Machine Learning Models]

What is interpretability? 

The definition of the verb interpret is “to explain or tell the meaning of: present in understandable terms” (Merriam- Webster 2019). Despite the apparent simplicity of this statement, the machine learning research community is struggling to agree upon a formal definition of the concept of interpretability/explainability. In the last years, in the room left by this lack of formalism, many methodologies have been proposed based on different “interpretations” (pun intended) of the above definition. While the proliferation of this multitude of disparate algorithms has posed challenges on rigorously comparing them, it is nevertheless interesting and useful to apply these techniques to analyze the behavior of deep learning models. 

What is this tutorial about? 

This tutorial focuses on illustrating some of the recent advancements in the field of interpretable deep learning. We will show common techniques that can be used to explain predictions on pre-trained models and that can be used to shed light on their inner mechanisms. The tutorial is aimed to strike the right balance between theoretical input and practical exercises. The session has been designed to provide the participants not only with the theory behind deep learning interpretability, but also to offer a set of frameworks and tools that they can easily reuse in their own projects. 

Interpretability In Deep Learning

Depiction: a framework for explainability 

The group of Cognitive Health Care and Life Sciences at IBM Research Zürich has open-sourced a python toolbox, depiction, with the aim of providing a framework to ease the application of explainability methods on custom models, especially for less experienced users. The module provides wrappers for multiple algorithms and is continuously updated including the latest algorithms from AIX360. The core concept behind depiction is to allow users to seamlessly run state-of-art interpretability methods with minimal requirements in terms of programming skills. Below an example of how depiction can be used to analyze a pre-trained model. 

A simple example

Let’s assume to have a fancy model for classification of tabular data pre-trained in Keras and available at a public url. Explaining its predictions with depiction is easy as implementing a lightweight wrapper of depiction.model.core.Model where its predict method is overloaded.

Interpretability In Deep Learning

Once FancyModel is implemented, using any of the depiction.interpreters available in the library, is as easy as typing:

Interpretability In Deep Learning

The explanations generated depend on the specific interpreter used. For example, in the case of explanations generated using LIME (Ribeiro et al.), when using a Jupyter notebook, one can simply run:

and directly obtain the model-specific explanation: 

Interpretability In Deep Learning

Want to know more? 

[Related Article: Not Always a Black Box: Machine Learning Approaches For Model Explainability]

If you found this blog post interesting and you want to know more about interpretability and depiction, come and join us at the tutorial Opening The Black Box—Interpretability In Deep Learningat ODSC Europe 2019  this November 20th in London.

Matteo Manica:

Interpretability In Deep LearningMatteo is a Research Staff Member in Cognitive Health Care and Life Sciences at IBM Research Zürich.
He’s currently working on the development of multimodal deep learning models for drug discovery using chemical features and omic data.
He also researches in multimodal learning techniques for the analysis of pediatric cancers in a H2020 EU project, iPC, with the aim of creating treatment models for patients.
He received his degree in Mathematical Engineering from Politecnico di Milano in 2013.
After getting his MSc he worked in a startup, Moxoff spa, as a software engineer and analyst for scientific computing.
In 2019 he obtained his doctoral degree at the end of a joint PhD program between IBM Research and the Institute of Molecular Systems Biology, ETH Zürich, with a thesis on multimodal learning approaches for precision medicine.

Joris Cadow:

Interpretability In Deep LearningJoris works as a Data Scientist in the IBM Research Zürich Lab (Rüschlikon, Switzerland). He joined the Cognitive Health Care and Life Sciences group initially for his master thesis of his degree in Computational Biology & Bioinformatics, a joint degree ETH Zürich and University Zürich.
His research interests include multimodal learning approaches, relational learning via GNNs (graph neural networks) and NLP.
He’s currently involved in different works focused on machine learning for precision medicine in the context of a H2020 EU project, iPC, with the goal of developing models for pediatric tumors.

ODSC Team

ODSC Team

ODSC gathers the attendees, presenters, and companies that are shaping the present and future of data science and AI. ODSC hosts one of the largest gatherings of professional data scientists with major conferences in USA, Europe, and Asia.

1