While applications of deep learning have produced impressive empirical results, the theory behind it is still poorly developed. However, a team of researchers from Intel and the Hebrew University are saying that they have made an important breakthrough that allows for a better theoretical understanding of the capabilities of deep learning.
The study focused on the capability of deep learning to simulate quantum computing computations. According to the researchers, their findings indicate that the key element explaining the success of deep learning is how information is “reused” in two of the most successful neural network types, convolutional neural nets (CNNs) and recurrent neural networks (RNNs).
Read more: Intel offers AI breakthrough in quantum computing
Special Series on Quantum Computing
The developments in the field of Quantum Computing are coming faster and faster. OODA analysts are focusing on what matters most to today’s business decision makers. Recent reporting includes:
- The Executive’s Guide To Quantum Computing: What business decision-makers need to know now about quantum superiority
- Is Quantum Computing Ushering in an Era of No More Secrets?: Context from OODA’s Matt Devost on the very near future of quantum computing.
- What To Do About Quantum Uncertainty: Guess what, besides uncertainty at a quantum level there is great uncertainty among business and policy makers regarding Quantum Computing.
- AI, quantum computing and 5G could make criminals more dangerous than ever, warn police: Quantum is one of many emerging technologies that law enforcement professionals are tracking
- Quantum Computing That Can Crack Modern Encryption More Than a Decade Away: When we see reports like this we wonder what qualifies the experts to say this. But in this case the experts are the National Academies of Sciences.
- Could quantum computers render current bitcoin and most blockchain cryptography powerless?: There is a worry that new algorithms that could run on quantum computing could attack blockchain and asymmetric encryption.