Combinatorial optimisation (CO) problems are among the hardest challenges in computer science, with real-world importance in logistics, transport, and energy systems. These problems involve choosing the “best” option from an astronomically large set of possibilities and are often NP-hard, meaning they become computationally intractable as the problem size grows. Neural solvers, advanced AI approaches designed… Read more »
Reinforcement learning (RL) has delivered some of AI’s most striking successes, from human-level Atari 1 play to world-class performance in Go2. Yet when applied to messy, real-world combinatorial optimisation (CO) problems such as energy grid management or autonomous logistics, even state-of-the-art RL systems can stall. Despite being trained to convergence, policies often hit a performance… Read more »
Multi-agent reinforcement learning (MARL) holds significant promise across domains such as autonomous driving, warehouse logistics, intelligent rail networks, and satellite alignment. Yet deploying MARL in the real world remains difficult. Training typically requires vast amounts of interactive data, which is both costly and potentially risky, particularly in safety-critical settings where trial and error is not… Read more »
InstaDeep is pleased to announce that a record five of its AI research papers have been accepted for presentation at the Thirty-sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022) with two papers in the main track and three workshop papers, including one authored in collaboration with BioNTech as part of our joint AI Innovation… Read more »
InstaDeep today announces that it has had three papers accepted for presentation at the 2021 Annual Conference on Neural Information Processing Systems (NeurIPS 2021), including one authored in collaboration with Google Research. NeurIPS2021 is the 35th edition of the highly prestigious annual machine learning conference, with sessions and workshop tracks presenting the latest research in… Read more »
Cape Town, 01 Oct 2020 – In 2018, Arnu Pretorius broke ground as the first African researcher to get a paper accepted at NeurIPS (Neural Information Processing Systems Conference), one of the most prestigious AI Conferences in the world. With “Critical initialisation for deep signal propagation in noisy rectifier neural networks” (arXiv:1811.00293v2), Arnu, still a… Read more »
The new year has kicked off, and we would like to take the time to reflect on our journey so far and share our thoughts on the two factors we believe will redefine the most important economic and political conversation of our time; the AI revolution and inequalities. OUR HIGHLIGHTS OF 2018 2018 has been… Read more »
We have a strong team present at NeurIPS this week, with exciting things on the agenda. We are proud to announce that — for the first time — two of our research papers will be presented, a huge milestone for us. Additionally, three of our colleagues including our CEO, Karim, are presenting in the workshop Black in AI (BAI)…. Read more »