Hardware-based machine learning acceleration

A computer-implemented method, comprising:

• partitioning, into a first batch of data and a second batch of data, an input data received at a hardware accelerator implementing a machine learning model, the input data comprising a continuous stream of data samples, and the input data being partitioned based at least on a resource constraint of the hardware accelerator;
• performing a real time update of a probability density function associated with the machine learning model, the probability density function being updated by at least processing, by the hardware accelerator, the first batch of data before the second batch of data;
• and
• generating, based at least on the updated probability density function, an output comprising a probability of encountering a data value.

A non-transitory computer readable medium storing instructions, which when executed by at least one data processor, result in operations comprising:

• partitioning, into a first batch of data and a second batch of data, an input data received at a hardware accelerator implementing a machine learning model, the input data comprising a continuous stream of data samples, and the input data being partitioned based at least on a resource constraint of the hardware accelerator;
• performing a real time update of a probability density function associated with the machine learning model, the probability density function being updated by at least processing, by the hardware accelerator, the first batch of data before the second batch of data;
• and
• generating, based at least on the updated probability density function, an output comprising a probability of encountering a data value.