Search

Implementations of artificial neural networks that borrow analogue techniques could potentially offer low-power alternatives to fully digital approaches1–3. One notable example is in-memory computing based on crossbar arrays of non-volatile memories4–7that execute, in an analogue manner, multiply–accumulate operations prevalent in artificial neural networks. Various non-volatile memories—including resistive memory8–13, phase-change memory14,15and flash memory16–19—have been used for such approaches. However, it remains challenging to develop a crossbar array of spin-transfer-torque magnetoresistive random-access memory (MRAM)20–22,  despite the technology’s practical advantages such as endurance and large-scale commercialization5. The difficulty stems from the low resistance of MRAM, which would result in large power consumption in a conventional crossbar array that uses current summation for analogue multiply–accumulate operations. Here we report a 64 × 64 crossbar array based on MRAM cells that overcomes the low-resistance issue with an architecture that uses resistance summation for analogue multiply–accumulate operations. The array is integrated with readout electronics in 28-nanometre complementary metal–oxide–semiconductor technology. Using this array, a two-layer perceptron is implemented to classify 10,000 Modified National Institute of Standards and Technology digits with an accuracy of 93.23 per cent (software baseline: 95.24 per cent). In an emulation of a deeper, eight-layer Visual Geometry Group-8 neural network with measured errors, the classification accuracy improves to 98.86 per cent (software baseline: 99.28 per cent). We also use the array to implement a single layer in a ten-layer neural network to realize face detection with an accuracy of 93.4 per cent.

ABSTRACTThe Dialogue-Awareness-*Tolerance (DA*T) Model stresses dialogue, intrapersonal and interpersonal, to (a) raise personal and community awareness, (b) reengage positive moral self-sanctioning mechanisms, (c) support those who are targets of intolerance, violence or harassment or have witnessed it, (d) stabilize and deescalate crisis and conflict situations, (e) acknowledge one’s vulnerability/discomfort/ambiguity in such dialogs, (f) increase tolerance to such reactions, (g) process the dissonance and (h) take action toward change. The DA*T Model incorporates and expands upon the processes of deconstructing the moment, critical incident stress debriefing, critical-dialogic intergroup dialogue and social action to make the experience manageable, safe and productive.

As Freud's privileged theory of unresolved grief, melancholia presents a compelling framework to conceptualize registers of loss and depression attendant to both psychic and material processes of Asian American immigration, assimilation, and racialization. Freud initially formulates melancholia as a pathological form of individual mourning for lost objects, places, or ideals. However, we propose a concept of melancholia as a depathologized structure of everyday group experience for Asian Americans. We analyze a number of Asian American cultural productions (literature and film) as well as two case histories of university students involving intergenerational conflicts and lost ideals of whiteness, Asianness, home, and language. Exploring these analyses against Klein's notions of lost objects, we propose a more refined theory of good and bad racialized objects. This theory raises the psychic and political difficulties of reinstatement and the mediation of the depressive position for Asian Americans. In addition, this theory suggests that processes of immigration, assimilation, and racialization are neither pathological nor permanent but involve the fluid negotiation between mourning and melancholia. Throughout this essay, we consider methods by which a more speculative approach to psychoanalytic theory and clinical practice might offer a deeper understanding of Asian American mental health issues.