InstaDeep’s DeepChain platform showcased at 2021 Festival of Biologics

InstaDeep was a proud Platinum Sponsor of the recent Festival of Biologics, held from the 9th to the 11th November 2021 in Basel, Switzerland, where it exhibited the company’s AI-powered protein design platform, DeepChain. The DeepChainTM product team was on-site at the Congress Center Basel throughout the Festival, showcasing the innovative AI-powered protein design platform. … Read more »

InstaDeep presents our DeepPack product for complex load optimisation in logistics at NVIDIA GTC conference

Following on from the company’s record four contributions to NVIDIA’s Spring GTC, InstaDeep is delighted to be participating in the global Autumn event with a presentation on how advanced decision making AI is being used to solve real life enterprise problems. GTC is being held fully online between 8-11 November and features a packed roster… Read more »

DeepChain hailed as a Biotech success story at INNOV’IN BIO

Organized by Connect’Innov in partnership with the Biotechpôle of Sidi Thabet, Innov’In Bio took place on 4-5 November and included plenary presentations and panel discussions, as well as a national competition for the best innovative projects in Biotechnology, Health and Well-being.  InstaDeep was invited to talk in the session on “Success Stories in Biotech”. Amine… Read more »

InstaDeep and AI Hub announce collaboration to benefit Tunisian AI ecosystem

InstaDeep is delighted to announce they are making a world-class NVIDIA A100 DGX supercomputing server and on-site support team available at The AI Hub located at the DOT innovation hub in central Tunis, for the exclusive benefit of the Tunisian Artificial Intelligence (AI) and Machine Learning (ML) ecosystem. This has been delivered in co-operation with… Read more »

IndabaX South Africa – Using MARL to Play StarCraft II

Continuing the company’s commitment to supporting and building the AI and ML community across Africa following the highly successful IndabaX Tunisia, InstaDeep is also organizing a session as part of IndabaX South Africa 2021. The South African event will run from 3 September – 26 November, and has been organised as an innovative ‘roadshow’ format… Read more »

InstaDeep Co-Founder and CWO, Zohra Slim, interviewed for leading “Connecting Africa” tech podcast

InstaDeep’s inspirational co-founder and CWO, Zohra Slim, was recently featured on the popular Connecting Africa podcast, hosted by Connecting Africa’s Paula Gilbert, Tobi Lafinhan and Tien Fu. During a wide-ranging conversation, Zohra spoke about her experiences as an African woman in tech, her entrepreneurial mindset and what challenges and opportunities she sees for the wider… Read more »

In this post, we introduce our first Meta-RL algorithm: MAML (Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks). With MAML, you can train agents that quickly adapt in almost any dense-reward environment. Let’s detail how it works.

Model Agnostic Meta-Learning made simple

(Part 2/4) In our introduction to meta-reinforcement learning, we presented the main concepts of meta-RL: Meta-Environments are associated with a distribution of distinct MDPs called tasks. The goal of Meta-RL is to learn to leverage prior experience to adapt quickly to new tasks. In Meta-RL, we learn an algorithm during a step called meta-training. At meta-testing, we apply this… Read more »

A simple introduction to Meta-Reinforcement Learning

A simple introduction to Meta-Reinforcement Learning

(Part 1/4) The recent developments in Reinforcement Learning (RL) have shown the incredible capacity of computers to outperform human performance in many environments such as Atari Games [1], Go, chess, shogi [2], Starcraft II [3]. This performance results from the development of Deep Learning and Reinforcement Learning methods like Deep Q-Networks (DQN) [4] and actor-critic methods [5, 6, 7, 8]. However, one essential advantage of… Read more »