|BIANCHI STEFANO||Cycle: XXXIII |
Tutor: SOTTOCORNOLA SPINELLI ALESSANDRO
Advisor: IELMINI DANIELE Major Research topic
:HARDWARE DESIGN AND IMPLEMENTATION OF MEMRISTIVE-BASED LEARNING SYSTEMS FOR EFFICIENT NEUROCOMPUTINGAbstract:
Neuromorphic engineering aims to reproduce brain-like reasoning in a silicon chip. Computers able to learn by sensory excitement from the external world, to infer abstract concepts and to make decisions, are spurring a new technological revolution reshaping all aspects of our life and society.
The development of artificial intelligent hardware systems must overcome the current architecture used for standard computers, which relies on physically separated processing unit and memory: data are continually sent to the processing unit from the memory, elaborated in the processor and then sent back again to the memory. Such repetitive transmission of information is the main difference with respect to the biological computation, where the knowledge is elaborated in the same place in which it is stored, hence “in-memory computing”.
In order to introduce a significant improvement in the hardware design, the scientific research has recently focused on the memristive devices such as the phase change memory (PCM) and the resistive random-access memory (RRAM). The main advantages of memristor devices is related to the 3D stacking capability in the back end of the line, which zeroes the transfer of information and enables “in situ” computation. For this reason, as well as for the great area efficiency (size of only few square-nm), the memristive devices are the best candidates to boost the next technological era.
This doctoral dissertation describes some novel approaches to boost the artificial intelligent computation by both bio-inspired and artificial intelligent standpoints.
Concerning the bio-inspired learning algorithms, the STDP (Spike-Timing-Dependent Plasticity) is among the most plausible paradigms accepted for the description of the learning activity in the human brain. For this reason, STDP is here verified by simulations and experimental measurements in extended networks with resistive random-access memory (RRAM) used as synapses. Great attention is also given to the prediction of the behavior of the bio-inspired networks via accurate analytical models. Furthermore, the Verilog-A modelling of the memristive devices is also investigated in order to introduce a complete framework for the simulation of memristor-based circuits in computer-based drafting tools.
On the other hand, the pure algorithmic approach to artificial intelligence has led to the definition of deep neural networks based on training algorithms, such as backpropagation, able to perform complex tasks. These techniques, which rely on a large number of arithmetical operations (matrix-vector multiplications, MVMs), demonstrated high reliability and efficiency in fully connected and convolutional neural networks for object recognition, natural language processing and playing games. However, despite of the significant efficiency in specific tasks, the artificial neural networks lack the sufficient plasticity for the adaptation to continually evolving situations.
To both rely on the computational accuracy of convolutional networks and on the bio-inspired plasticity and resilience of STDP, a new kind of artificial neural network is here proposed. The new architecture is capable of learning and classifying new input objects without catastrophically forgetting previously learnt information, thus achieving lifelong learning. The efficacy of the neural network is highlighted by PCM-based experimental demonstrations of continual learning for the MNIST and CIFAR10 datasets, with particular attention on the cohesion of stability and plasticity enabled by the multilevel programming of the PCM devices.
In order to introduce a further computational novelty in terms of performances and resilience in the neuromorphic engineering, this doctoral dissertation also proposes a new PCM-based homeostatic neuron. At each fire event, an internal PCM device is partially crystallized, thus modulating the internal threshold of the neuron. This assures improved pattern specialization, significant reduction of power consumption, robustness against external perturbations and self-control of each neuronal activity as a function of the of spiking rate. The homeostatic neuron is also shown to enable multi-pattern learning from Fashion-MNIST dataset via unsupervised asynchronous STDP.
The PCM-based neuron is also useful in the framework of reinforcement learning, where the interaction with the surrounding environment contributes to the evolution of the network dynamics. Concerning the bio-inspired recurrent neural networks (RNNs), it is here demonstrated that the self-adaptation driven by PCM devices can control the internal states of the neurons in relation to the past experience of the full neural network, thus enabling the fulfillment of complex decision making tasks.
In order to validate the concept of reinforcement learning with memristive devices in a large scale, an extended hardware system is also presented. In particular, the hardware is capable of reproducing bio-plausible cognitive functions with a SiOx RRAM-based architecture mastered by a digital system on chip (SoC). The computation of the system carries out significant results by merging Hebbian learning and homeostatic plasticity for improved efficiency and stability in bio-inspired RNNs. The hardware is tested for two main tasks: (i) the autonomous exploration of a continually evolving maze (i.e. a maze whose walls continually move in time); (ii) the Mars rover navigation, which concerns the exploration of Martian landscapes by using the NASA database of images. The hardware self-optimizes its policy starting from stochastic trials and plastically modifies its synaptic connections to reach the optimum escape path by progressive experience of penalties and rewards.
The integrated design of memristor-based neural networks, along with the definition of robust circuital architectures, promises significant breakthroughs in the future thanks to the enormous advantages in terms of compactness, efficiency and speed of memristive devices. In particular, this doctoral dissertation also proposes the integrated design of a fully connected artificial neural network using the software design kit STMicroelectronics BCD 90 nm with embedded PCM cells. The memristor-based computation enables the use of only one-clock computation per single MVM, which is tremendously more advantageous with respect to the thousands of digital multiply and accumulate operations (MACs), each requiring at least one clock pulse, currently needed by standard Von Neumann computers. Furthermore, significant improvements in terms of hardware architecture are also proposed since the design is robust against device non-idealities such as the conductance drift of the PCM devices.
The results achieved during this doctoral study offer a wide range of analysis in various fields, ranging from pure modelling to systems and integrated designs. In the future, both the research lines related to bio-inspired and artificial intelligent computations are going to spur a new technological era for the human society, always hoping for a better future based on the investigation of nature and technology.
After all, the limit of the scientific research is only the imagination.