Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

The accumulation and extrusion of Ca2+ in the pre- and postsynaptic compartments play a critical role in initiating plastic changes in biological synapses. To emulate this fundamental process in electronic devices, we developed diffusive Ag-in-oxide memristors with a temporal response during and after stimulation similar to that of the synaptic Ca2+ dynamics. In situ high-resolution transmission electron microscopy and nanoparticle dynamics simulations both demonstrate that Ag atoms disperse under electrical bias and regroup spontaneously under zero bias because of interfacial energy minimization, closely resembling synaptic influx and extrusion of Ca2+, respectively. The diffusive memristor and its dynamics enable a direct emulation of both short- and long-term plasticity of biological synapses, representing an advance in hardware implementation of neuromorphic functionalities.

/pdf/memristors-with-diffusive-dynamics-as-synaptic-emulators-for-4j06bmhu3f.pdf

Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing

The computational brain: Patricia S. Churchland and Terrence J. Sejnowski (MIT Press, Cambridge, MA, 1992); xi, 544 pages, $39.95

The electronic properties of inorganic devices such as memristors can be used to simulate neurological behaviour. In particular, ionic and electronic effects in a silver sulphide device are now shown to mimic short- and long-term synaptic functions. Memory is believed to occur in the human brain as a result of two types of synaptic plasticity: short-term plasticity (STP) and long-term potentiation (LTP; refs 1, 2, 3, 4). In neuromorphic engineering5,6, emulation of known neural behaviour has proven to be difficult to implement in software because of the highly complex interconnected nature of thought processes. Here we report the discovery of a Ag2S inorganic synapse, which emulates the synaptic functions of both STP and LTP characteristics through the use of input pulse repetition time. The structure known as an atomic switch7,8, operating at critical voltages, stores information as STP with a spontaneous decay of conductance level in response to intermittent input stimuli, whereas frequent stimulation results in a transition to LTP. The Ag2S inorganic synapse has interesting characteristics with analogies to an individual biological synapse, and achieves dynamic memorization in a single device without the need of external preprogramming. A psychological model related to the process of memorizing and forgetting is also demonstrated using the inorganic synapses. Our Ag2S element indicates a breakthrough in mimicking synaptic behaviour essential for the further creation of artificial neural systems that emulate characteristics of human memory.

/pdf/short-term-plasticity-and-long-term-potentiation-mimicked-in-3c6onjbc0r.pdf

Short-term plasticity and long-term potentiation mimicked in single inorganic synapses

Modern computers are based on the von Neumann architecture in which computation and storage are physically separated: data are fetched from the memory unit, shuttled to the processing unit (where computation takes place) and then shuttled back to the memory unit to be stored. The rate at which data can be transferred between the processing unit and the memory unit represents a fundamental limitation of modern computers, known as the memory wall. In-memory computing is an approach that attempts to address this issue by designing systems that compute within the memory, thus eliminating the energy-intensive and time-consuming data movement that plagues current designs. Here we review the development of in-memory computing using resistive switching devices, where the two-terminal structure of the devices, their resistive switching properties, and direct data processing in the memory can enable area- and energy-efficient computation. We examine the different digital, analogue, and stochastic computing schemes that have been proposed, and explore the microscopic physical mechanisms involved. Finally, we discuss the challenges in-memory computing faces, including the required scaling characteristics, in delivering next-generation computing. This Review Article examines the development of in-memory computing using resistive switching devices.

/pdf/in-memory-computing-with-resistive-switching-devices-1mv368csjy.pdf

In-memory computing with resistive switching devices

Competitive learning is a general technique for training clustering and classification networks. We have developed an 11-transistor silicon circuit, that we term an automaximizing bump circuit, that uses silicon physics to naturally implement a similarity computation, local adaptation, simultaneous adaptation and computation and nonvolatile storage. This circuit is an ideal building block for constructing competitive-learning networks. We illustrate the adaptive nature of the automaximizing bump in two ways. First, we demonstrate a silicon competitive-learning circuit that clusters one-dimensional (1-D) data. We then illustrate a general architecture based on the automaximizing bump circuit; we show the effectiveness of this architecture, via software simulation, on a general clustering task. We corroborate our analysis with experimental data from circuits fabricated in a 0.35-/spl mu/m CMOS process.

/pdf/competitive-learning-with-floating-gate-circuits-2qonrjlis7.pdf

Competitive learning with floating-gate circuits

We have developed a new floating-gate silicon MOS transistor for analog learning applications. The memory storage is nonvolatile; hot-electron injection and electron tunneling permit bidirectional memory updates. Because these updates depend on both the stored memory value and the transistor terminal voltages, the synapse can implement a learning function. We have derived a memory-update rule from the physics of the tunneling and injection processes, and have investigated synapse learning in a prototype array. Unlike conventional EEPROM devices, the synapse allows simultaneous memory reading and writing. Synapse transistor arrays can therefore compute both the array output, and local memory updates, in parallel. The synapse is small, and typically is operated at subthreshold current levels; it will permit the development of dense, low-power silicon learning systems.

/pdf/a-single-transistor-silicon-synapse-cyb652zk69.pdf

A single-transistor silicon synapse

The availability of inexpensive CMOS technologies that perform well at microwave frequencies has created new opportunities for automated material handling within supply chain management (SCM) that in hindsight, be viewed as revolutionary. This article outlines the system architecture and circuit design considerations that influence the development of radio frequency identification (RFID) tags through a case study involving a high-performance implementation that achieves a throughput of nearly 800 tags/s at a range greater than 10 m. The impact of a novel circuit design approach ideally suited to the power and die area challenges is also discussed. Insights gleaned from first-generation efforts are reviewed as an object lesson in how to make RFID technology for SCM, at a cost measured in pennies per tag, reach its full potential through a generation 2 standard.

Design of ultra-low-cost UHF RFID tags for supply chain applications

An RFID integrated circuit includes a demodulator to receive a first signal, the first signal having been generated by an RFID reader responsive to detection of a first environmental condition. The RFID integrated circuit further includes a controller to set, based on the first signal, a modulation format for the RFID integrated circuit and to configure the RFID integrated circuit to modulate a backscatter signal according to the modulation format.

Method and apparatus to configure an RFID system to be adaptable to a plurality of environmental conditions

We have developed a bandpass floating-gate amplifier that uses tunneling and pFET hot-electron injection to set its dc operating point adaptively. Because the hot-electron injection is an inherent part of the pFET's behavior, we obtain this adaptation with no additional circuitry. Because the gate currents are small, the circuit exhibits a high-pass characteristic with a cutoff frequency less than 1 Hz. The high-frequency cutoff is controlled electronically, as is done in continuous-time filters. We have derived analytical models that completely characterize the amplifier and that are in good agreement with experimental data for a wide range of operating conditions and input waveforms. This autozeroing floating-gate amplifier demonstrates how to use continuous-time floating-gate adaptation in amplifier design.

/pdf/an-autozeroing-floating-gate-amplifier-41c6zmvm1j.pdf

Christopher J. Diorio

Papers

Competitive learning with floating-gate circuits

A single-transistor silicon synapse

Design of ultra-low-cost UHF RFID tags for supply chain applications

Method and apparatus to configure an RFID system to be adaptable to a plurality of environmental conditions

An autozeroing floating-gate amplifier