The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Deep Reinforcement Learning for Logistics at Instadeep with Karim Beguir - #302

Sep 25, 2019

43:53

Creator website

AI Chapters

Episode notes

Introduction

2min

Instadip's Focus: Building Advanced Decision-Making Systems for the Enterprise

2min

The Rise of Reinforcement Learning in Logistics

2min

The Gaps in Deep Learning and Machine Learning Approaches

4min

How to Apply Deep Learning to a Problem Like the Right-Sharing Problem

2min

How to Optimize Your Ride-Sharing

2min

How to Train a Realistic Environment of a City

2min

The Open Source Simulator for Open Street Maps

2min

Generalization and Transfer Learning

3min

10.

Transfer Learning for Computer Vision

2min

11.

The Effects of Bin Packing Shape on Transfer Learning

1min

12.

The Complexity of RL in Algorithms

2min

13.

How to Use Heuristics to Improve Deep Learning

3min

14.

The Advantages and Disadvantages of Learning Based Solutions

3min

15.

The Importance of Explainability in Deep Learning

3min

16.

How to Remove Spurious Cases From Your Reward System

2min

17.

The Power of Constraints

2min

18.

Reinforcement Learning: The Key to a Smart System

3min

19.

The Impact of Machine Learning Systems on Decision Making

3min

Today we are joined by Karim Beguir, Co-Founder and CEO of InstaDeep, a company focusing on building advanced decision-making systems for the enterprise. In this episode, we focus on logistical problems that require decision-making in complex environments using deep learning and reinforcement learning. Karim explains the InstaDeep process and mindset, where they get their data sets, the efficiency of RL, heuristic vs learnability approaches and how explainability fits into the model.