Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. Consequently, lifelong learning capabilities are crucial for computational systems and autonomous agents interacting in the real world and processing continuous streams of information. However, lifelong learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which information becomes incrementally available over time.
Come and join us to deep dive into the deep learning/continual learning and gain the latest innovations in the field. During this internship, you will focus on:

• Extensive research and implement the state-of-the-art of continual learning and neural network.
• Improve current continual learning pipeline.
• Innovative solution using the existing literature and the intern’s knowledge of machine learning.
• Contribute to the development of our solution, both improving our current algorithms in production and helping to lay the foundations of future iterations.

• Pursuing an MSc / MEng degree in computer science, applied mathematics or any related technical field
• Prior experience in building and training deep learning / machine learning algorithms
• Good theoretical knowledge in computer vision, neural networks, and other DL techniques
• Excellent coding skills in python (experience with pytorch is a plus)
• Great sense of initiative, autonomy and scientific rigour
• Curiosity and a strong interest for DL/ML topics and the latest scientific breakthrough
• Proficiency in English (ability to quickly read and understand research papers)
• Prior experience with Git and collaborative tools is a plus
• Personal side projects or Kaggle competitions are a plus

• Quick screening call
• Technical test, to be completed at home
• Final interview, including a technical part, and a meeting with different members of the R&D team to evaluate your motivation / cultural fit