1 files changed, 134 insertions, 0 deletions
diff --git a/refs/hw_research_claims.json b/refs/hw_research_claims.json
new file mode 100644
index 0000000..12b6206
--- /dev/null
+++ b/refs/hw_research_claims.json
@@ -0,0 +1,134 @@
+[
+ {
+  "claim": "The Mythic M1076 Analog Matrix Processor uses analog compute-in-memory to perform matrix multiplication (MVM) on-chip without external DRAM/memory, storing up to 80 million weights on a single chip.",
+  "source": "https://mythic.ai/products/m1076-analog-matrix-processor/",
+  "quote": "Capacity for up to 80M weights - able to run single or multiple complex DNNs entirely on-chip ... execute matrix multiplication operations without any external memory",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The M1076 is an inference-only accelerator: DNN models are trained off-device and then programmed into the chip for inference, with no described support for online/in-situ weight updates inside a training loop.",
+  "source": "https://mythic.ai/products/m1076-analog-matrix-processor/",
+  "quote": "DNN models...then programmed into the Mythic AMP for inference",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The IBM HERMES chip is a 64-core mixed-signal in-memory compute chip fabricated in 14 nm CMOS with backend-integrated phase-change memory (PCM), with each core holding a 256x256 analog weight matrix, for up to 4,194,304 (~4.2 million) weights stored on a single chip using over 16 million PCM devices (four PCM devices per unit cell).",
+  "source": "https://www.nature.com/articles/s41928-023-01010-1",
+  "quote": "up to 4,194,304 weights can be stored on the chip ... 64 AIMC cores interconnected via an on-chip communication network ... Four PCM devices per unit cell (two for each polarity)",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The chip is inference-only: weights are programmed once via offline hardware-aware training before deployment, and it does not support in-situ / online weight update inside a training loop (making it unsuitable as-is for Equilibrium Propagation's local in-situ weight updates).",
+  "source": "https://www.nature.com/articles/s41928-023-01010-1",
+  "quote": "Inference-only; supports offline training with \"hardware-aware training\" before deployment.",
+  "vote": "3-0"
+ },
+ {
+  "claim": "A memristor-based compute-in-memory module performs vector-matrix multiplication (VMM) in situ and in parallel \u2014 directly relevant to the analog MVM substrate sought for the EP relaxation feedback path.",
+  "source": "https://arxiv.org/abs/2305.14547",
+  "quote": "Memristor-based compute-in-memory (CIM) modules can perform vector-matrix multiplication (VMM) in situ and in parallel, and have shown great promises in DNN inference applications.",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The work experimentally implements an on-chip mixed-precision TRAINING scheme (not inference-only) on a bulk-switching memristor CIM module, demonstrating in-situ weight update during training rather than one-time-programmed fixed weights.",
+  "source": "https://arxiv.org/abs/2305.14547",
+  "quote": "In this work, we experimentally implement a mixed-precision training scheme to mitigate these effects using a bulk-switching memristor CIM module.",
+  "vote": "3-0"
+ },
+ {
+  "claim": "Weight updates are accumulated in digital units at high precision and the analog memristor devices are only physically programmed when the accumulated update exceeds a threshold \u2014 a concrete mechanism for fast online weight update that limits write frequency/endurance stress, exactly the kind of hybrid-update scheme an EP training loop needs.",
+  "source": "https://arxiv.org/abs/2305.14547",
+  "quote": "Lowprecision CIM modules are used to accelerate the expensive VMM operations, with high precision weight updates accumulated in digital units. Memristor devices are only changed when the accumulated weight update value exceeds a pre-defined threshold.",
+  "vote": "3-0"
+ },
+ {
+  "claim": "Most memristor/ReRAM in-memory ML accelerators are designed for inference-only workloads that deliberately avoid frequent weight updates, because of high write energy and limited write endurance \u2014 meaning in-situ/online training (required for EP) is not the dominant design target.",
+  "source": "https://arxiv.org/html/2501.12644v1",
+  "quote": "Most memristor-based machine learning accelerators target workloads that avoid frequent memristor updates because of high write energy and limited endurance.",
+  "vote": "3-0"
+ },
+ {
+  "claim": "Attention-based models like Transformers require frequent updates of K, V, and Q matrices, unlike standard inference where weights are stationary \u2014 a property that conflicts with memristor crossbars' weakness at frequent reprogramming and is flagged as an open hardware challenge.",
+  "source": "https://arxiv.org/html/2501.12644v1",
+  "quote": "Unlike conventional neural network inference, where all weights are stationary, models with attention mechanisms, such as Transformers, require frequent updates of K, V, and Q matrices and computation with them.",
+  "vote": "3-0"
+ },
+ {
+  "claim": "In-situ (on-chip) training of MLP, CNN, LSTM, and reinforcement-learning models has been experimentally demonstrated on memristor crossbar platforms, establishing that local in-array weight updates during a learning loop are physically achievable on memristive hardware.",
+  "source": "https://arxiv.org/html/2501.12644v1",
+  "quote": "Soon after, various ML algorithms have been experimentally implemented on the same platform, including in-situ training of multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM) and reinforcement learning(RL).",
+  "vote": "3-0"
+ },
+ {
+  "claim": "Memristive crossbar weight reprogramming is constrained by limited non-volatile memory (NVM) endurance, which restricts the number of times memristors can be rewritten \u2014 a fundamental obstacle for in-situ training loops that require repeated weight updates.",
+  "source": "https://arxiv.org/abs/2410.21730",
+  "quote": "Our idea addresses the limited non-volatile memory endurance, which restrict the number of times they can be reprogrammed.",
+  "vote": "2-1"
+ },
+ {
+  "claim": "This work deliberately avoids on-chip/in-situ training for MRAM in-memory computing, instead programming weights once via off-chip adaptive quantization and keeping them fixed during inference \u2014 i.e., it is an inference-only approach, not online in-situ weight update.",
+  "source": "https://www.science.org/doi/10.1126/sciadv.adp3710",
+  "quote": "off-chip adaptive training method to adjust deep neural network parameters, achieving accurate AiMC inference",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The authors state that in-situ/on-chip training, while optimal for accuracy, increases energy consumption and degrades device programming lifespan \u2014 the motivating reason analog in-memory substrates avoid online weight updates (directly relevant to EP's requirement for repeated in-situ updates).",
+  "source": "https://www.science.org/doi/10.1126/sciadv.adp3710",
+  "quote": "in situ training achieves optimal accuracy, the on-chip update cycles increase energy consumption and reduce memristor programming life span",
+  "vote": "3-0"
+ },
+ {
+  "claim": "RRAM/memristor devices suffer non-idealities that directly constrain in-situ trainability: high variability, asymmetric and nonlinear weight update, limited endurance, retention loss, and stuck-at-faults.",
+  "source": "https://escholarship.org/uc/item/4t9278vc",
+  "quote": "they suffer from numerous nonidealities limiting performance, including high variability, asymmetric and nonlinear weight update, endurance, retention and stuck at fault (SAF)",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The thesis develops methods for online (in-situ) training of memristive crossbars under stochastic asymmetric nonlinear weight update, including a compensation technique (small-scale) and stochastic rounding (tested on spiking neural networks) \u2014 i.e., memristive crossbars can be trained with weights updated inside the loop, not just one-time programmed.",
+  "source": "https://escholarship.org/uc/item/4t9278vc",
+  "quote": "developed a model to incorporate stochastic asymmetric nonlinear weight update in online (in-situ) training, proposing solutions including a compensation technique tested on small-scale problems and stochastic rounding tested on spiking neural networks",
+  "vote": "3-0"
+ },
+ {
+  "claim": "Weight programming here is INFERENCE-ONLY / one-time: it is treated as a one-time cost computed per DNN, not an in-situ/online update inside a training loop. This places PCM crossbars in this regime in the LARGE-but-fixed-weight category, failing EP's critical in-situ-update filter.",
+  "source": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9247051/",
+  "quote": "weight programming optimisation represents a one-time computational cost that should be performed for each unique DNN and unique set of underlying analogue memory device characteristics.",
+  "vote": "3-0"
+ },
+ {
+  "claim": "A physical analog electronic network of self-adjusting nonlinear transistor-based resistive elements learns nonlinear tasks (XOR, nonlinear regression) entirely in-situ without a computer/processor and without backpropagation, using the local Coupled Learning rule explicitly described as closely related to Equilibrium Propagation and Contrastive Hebbian Learning.",
+  "source": "https://www.pnas.org/doi/10.1073/pnas.2319718121",
+  "quote": "Here we introduce a nonlinear learning metamaterial -- an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR and nonlinear regression, without a computer. ... ac",
+  "vote": "3-0"
+ },
+ {
+  "claim": "Weights are physically adjustable in-situ: each edge's learning degree of freedom is a transistor gate voltage stored on a local capacitor (C0 = 22 uF), and dedicated on-edge circuitry continuously updates it by charging/discharging based on the local difference between a 'free' and a 'clamped' twin network \u2014 a physically realized free-phase/nudged-phase contrastive update with no central gradient computation.",
+  "source": "https://www.pnas.org/doi/10.1073/pnas.2319718121",
+  "quote": "During training, circuitry on each twin edge continuously updates G by charging or discharging the local capacitor, depending on the local difference between the electronic states in the two networks. ... We designate one network as 'Free' and impose only inputs (V1 , V- ), and the other as 'Clamped",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The forward computation is physical settling: the analog network relaxes to an equilibrium steady state on a ~1 microsecond timescale (tau_V ~ 1 us), so the relaxation IS the physical circuit dynamics rather than a digital iteration, and learning updates evolve on a slower 18 ms timescale.",
+  "source": "https://www.pnas.org/doi/10.1073/pnas.2319718121",
+  "quote": "the network 'calculates' the output (orange) naturally from the inputs ... reaches equilibrium on a timescale of tau_V ~ 1 us ... They will evolve with timescale tau0 = 18 ms until frozen, or until the system reaches a state where the two networks have",
+  "vote": "3-0"
+ },
+ {
+  "claim": "Equilibrium Propagation has been physically realized on a commercial hardware substrate: the D-Wave quantum-annealing Ising machine, where the physical machine performs both the free-phase and nudge-phase relaxation to a steady state (the settling is physical, not simulated).",
+  "source": "https://www.nature.com/articles/s41467-024-46879-4",
+  "quote": "Employing the commercial D-Wave Ising machine, composed of thousands of two-state components... we utilized the quantum annealing procedure of the D-Wave chip to achieve the free phase of EP... The steady states of the spins at the end of the free and nudge phase are measured, recorded, and used to ",
+  "vote": "3-0"
+ },
+ {
+  "claim": "The weights are NOT stored or updated in-situ on the analog/quantum substrate; they live on a classical digital computer, where the input-weight product and the SGD weight update are computed, and only bias fields and couplings are loaded onto the chip each phase. This makes it an inference-only / externally-trained substrate from the EP-in-situ-learning standpoint.",
+  "source": "https://www.nature.com/articles/s41467-024-46879-4",
+  "quote": "we calculate the product of the input data X (an input image, for instance) and a trainable weight matrix Winput using a digital computer... The updates are then applied to the weights using the standard stochastic gradient descent algorithm",
+  "vote": "1-1"
+ },
+ {
+  "claim": "The learning rule is local: weight updates are derived purely from local measurements of the two equilibrium (free and nudged) states, explicitly avoiding backpropagation's non-local computation \u2014 validating EP/local backprop-free learning as a viable training rule on physical equilibrium hardware.",
+  "source": "https://www.nature.com/articles/s41467-024-46879-4",
+  "quote": "The parameter changes required for learning are derived from local measurements of the equilibrium states, as opposed to a complex non-local analytic mathematical procedure like backpropagation",
+  "vote": "3-0"
+ }
+]
+\ No newline at end of file