The design of DNN accelerators includes two key parts: HW resource configuration and mapping strategy. Intensive research has been conducted to optimize each of them independently. Unfortunately, optimizing for both together is extremely challenging due to the extremely large cross-coupled search space. To address this, in this paper, we propose a HW-Mapping co-optimization framework, an efficient encoding of the immense design space constructed by HW and Mapping, and a domain-aware genetic algorithm, named DiGamma, with specialized operators for improving search efficiency. We evaluate DiGamma with seven popular DNNs models with different properties. Our evaluations show DiGamma can achieve (geomean) 3.0x and 10.0x speedup, comparing to the best-performing baseline optimization algorithms, in edge and cloud settings.

We are very excited to announce that Digamma.ai was selected to receive Microsoft AI for Earth Innovation Grant to apply Artificial Intelligence to help understand and protect the planet. AI for Earth awards grants to support projects that use AI to change the way people and organizations monitor, model, and manage Earth's natural systems. To date, they have awarded 435 grants to projects with impact in 71 countries. Our team will use the funds to continue and expand their work with U.S. Geological Survey to apply state-of-the-art Machine Learning algorithms towards the study of landslides and other natural hazards. The main objective of the partnership between Digamma.ai and USGS is not only to find the location of the landslides, but to gain a better understanding of the landscape responses to earthquakes and large storms.

Everyone is talking about AI applications for healthcare, financial services and self-driving cars. At the same time, creative occupations were previously understood to be immune from the disruptions of AI due to the high levels of intuition and gut instinct, difficult to replicate by complex algorithms, but that is changing now. In this post, I want to talk about 7 lesser-known ways Artificial Intelligence is changing the world around us. Some of these applications might surprise you. The art and science of perfume making is a complex process that takes years to master, but now this task of evoking olfactory senses is being done by Artificial Intelligence.

With a methodology driven by both academic research in AI and real-life engineering experience, Digamma.ai's machine learning consultants deliver intelligent and pragmatic AI solutions to complex problems. Our strategy works -- for over fourteen years, we have successfully solved complex technological and business challenges at Codeminders. Digamma.ai is the artificial intelligence branch of Codeminders. Our AI-focused engineering team combines rigorous research methodologies from leading U.S. and European universities with hands-on problem-solving skills.

We characterize the combinatorial structure of conditionally-i.i.d. sequences of negative binomial processes with a common beta process base measure. In Bayesian nonparametric applications, such processes have served as models for latent multisets of features underlying data. Analogously, random subsets arise from conditionally-i.i.d. sequences of Bernoulli processes with a common beta process base measure, in which case the combinatorial structure is described by the Indian buffet process. Our results give a count analogue of the Indian buffet process, which we call a negative binomial Indian buffet process. As an intermediate step toward this goal, we provide a construction for the beta negative binomial process that avoids a representation of the underlying beta process base measure. We describe the key Markov kernels needed to use a NB-IBP representation in a Markov Chain Monte Carlo algorithm targeting a posterior distribution.