All Stories

  1. Refined Two-Sided Learning Rate Tuning for Robust Evaluation in Federated Learning
  2. FedAGF: Adaptive Concurrency via Gradient Feedback for Mitigating Extreme Label Skew in Budget-Constrained Federated Learning
  3. Runtime Feature Compression for Adaptive Keyword Spotting on Embedded Systems
  4. Reducing the Energy Consumption of sEMG-Based Gesture Recognition at the Edge Using Transformers and Dynamic Inference
  5. Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays
  6. Automatic Layer Freezing for Communication Efficiency in Cross-Device Federated Learning
  7. Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks
  8. Monocular Depth Perception on Microcontrollers for Edge Applications
  9. Energy-Quality Scalable Monocular Depth Estimation on Low-Power CPUs
  10. Communication-Efficient Federated Learning with Gradual Layer Freezing
  11. Dynamic ConvNets on Tiny Devices via Nested Sparsity
  12. AxP: A HW-SW Co-Design Pipeline for Energy-Efficient Approximated ConvNets via Associative Matching
  13. ACME: An Energy-Efficient Approximate Bus Encoding for I2C
  14. Ultra-compact binary neural networks for human activity recognition on RISC-V processors
  15. TVFS: Topology Voltage Frequency Scaling for Reliable Embedded ConvNets
  16. Manufacturing as a Data-Driven Practice: Methodologies, Technologies, and Tools
  17. EAST: Encoding-Aware Sparse Training for Deep Memory Compression of ConvNets
  18. TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks
  19. Efficacy of Topology Scaling for Temperature and Latency Constrained Embedded ConvNets
  20. Logic Synthesis of Pass-Gate Logic Circuits With Emerging Ambipolar Technologies
  21. Corrigendum to“Approximate error detection-correction for efficient adaptive voltage Over-Scaling”[Integration 63 (2018) 220–231]
  22. Fast and Accurate Inference on Microcontrollers With Boosted Cooperative Convolutional Neural Networks (BC-Net)
  23. Performance Profiling of Embedded ConvNets under Thermal-Aware DVFS
  24. CoopNet: Cooperative Convolutional Neural Network for Low-Power MCUs
  25. Integer ConvNets on Embedded CPUs: Tools and Performance Assessment on the Cortex-A Cores
  26. Arbitrary-Precision Convolutional Neural Networks on Low-Power IoT Processors
  27. Inference on the Edge: Performance Analysis of an Image Classification Task Using Off-The-Shelf CPUs and Open-Source ConvNets
  28. Implementing Adaptive Voltage Over-Scaling: Algorithmic Noise Tolerance vs. Approximate Error Detection
  29. Enabling Energy-Efficient Unsupervised Monocular Depth Estimation on ARMv7-Based Platforms
  30. Energy-Efficient Convolutional Neural Networks via Recurrent Data Reuse
  31. SAID: A Supergate-Aided Logic Synthesis Flow for Memristive Crossbars
  32. Optimality Assessment of Memory-Bounded ConvNets Deployed on Resource-Constrained RISC Cores
  33. Energy-Accuracy Scalable Deep Convolutional Neural Networks: A Pareto Analysis
  34. On the Efficiency of Early Bird Sampling (EBS) an Error Detection-Correction Scheme for Data-Driven Voltage Over-Scaling
  35. Layer-Wise Compressive Training for Convolutional Neural Networks
  36. Logic-In-Memory Architecture For Min/Max Search
  37. Adaptive Convolutional Neural Networks
  38. Energy-Driven Precision Scaling for Fixed-Point ConvNets
  39. Inferential Logic: a Machine Learning Inspired Paradigm for Combinational Circuits
  40. Approximate Error Detection-Correction for efficient Adaptive Voltage Over-Scaling
  41. Quasi-exact logic functions through classification trees
  42. Weak-MAC: Arithmetic Relaxation for Dynamic Energy-Accuracy Scaling in ConvNets
  43. Design-Space Exploration of Pareto-Optimal Architectures for Deep Learning with DVFS
  44. Multiplication by Inference using Classification Trees: A Case-Study Analysis
  45. All-digital embedded meters for on-line power estimation
  46. Energy-performance design exploration of a low-power microprogrammed deep-learning accelerator
  47. A compression-driven training framework for embedded deep neural networks
  48. Early bird sampling: A short-paths free error detection-correction strategy for data-driven VOS
  49. Activation-Kernel Extraction through Machine Learning
  50. Tunable Error Detection-Correction for Efficient Adaptive Voltage Over-Scaling
  51. Beyond Ideal DVFS Through Ultra-Fine Grain Vdd-Hopping
  52. Logic Synthesis for Silicon and Beyond-Silicon Multi-gate Pass-Logic Circuits
  53. Quasi-Adiabatic Logic Arrays for Silicon and Beyond-Silicon Energy-Efficient ICs
  54. Ultra-Fine Grain Vdd-Hopping for energy-efficient Multi-Processor SoCs
  55. Multi-function logic synthesis of silicon and beyond-silicon ultra-low power pass-gates circuits
  56. Enabling quasi-adiabatic logic arrays for silicon and beyond-silicon technologies
  57. Graphene-PLA (GPLA)
  58. Ultra-low power circuits using graphene p–n junctions and adiabatic computing
  59. An automated design flow for approximate circuits based on reduced precision redundancy
  60. One-pass logic synthesis for graphene-based Pass-XNOR logic circuits
  61. Characterizing the Activity Factor in NBTI Aging Models for Embedded Cores
  62. Design and Characterization of Analog-to-Digital Converters using Graphene P-N Junctions
  63. Exploiting the Expressive Power of Graphene Reconfigurable Gates via Post-Synthesis Optimization
  64. Evaluating a Hardware-Based Approach for Detecting Resistive-Open Defects in SRAMs
  65. Power-Gating for Leakage Control and Beyond
  66. Ultra Low-Power Computation via Graphene-Based Adiabatic Logic Gates
  67. Modeling of Physical Defects in PN Junction Based Graphene Devices
  68. Row-based body-bias assignment for dynamic thermal clock-skew compensation
  69. Dynamic Indexing: Leakage-Aging Co-Optimization for Caches
  70. Pass-XNOR logic: A new logic style for P-N junction based graphene circuits
  71. Modeling and characterization of thermally induced skew on clock distribution networks of nanometric ICs
  72. Power modeling and characterization of Graphene-based logic gates
  73. Exploration of different implementation styles for graphene-based reconfigurable gates
  74. Investigating the behavior of physical defects in pn-junction based reconfigurable graphene devices
  75. Technique based on On-Chip Current Sensors and Neighbourhood Comparison Logic to detect resistive-open defects in SRAMs
  76. Layout-Driven Post-Placement Techniques for Temperature Reduction and Thermal Gradient Minimization
  77. Delay model for reconfigurable logic gates based on graphene PN-junctions
  78. Energy-optimal SRAM supply voltage scheduling under lifetime and error constraints
  79. On-Chip NBTI and PBTI Tracking through an All-Digital Aging Monitor Architecture
  80. Design Techniques and Architectures for Low-Leakage SRAMs
  81. Design Techniques for NBTI-Tolerant Power-Gating Architectures
  82. NBTI-Aware Data Allocation Strategies for Scratchpad Based Embedded Systems
  83. Energy-optimal caches with guaranteed lifetime
  84. NBTI effects on tree-like clock distribution networks
  85. On-chip process variation-tracking through an all-digital monitoring architecture
  86. Power Efficient Variability Compensation Through Clustered Tunable Power-Gating
  87. A new Built-In Current Sensor scheme to detect dynamic faults in Nano-Scale SRAMs
  88. NBTI-aware data allocation strategies for scratchpad memory based embedded systems
  89. An On-Chip All-Digital PV-Monitoring Architecture for Digital IPs
  90. Buffering of frequent accesses for reduced cache aging
  91. Sub-Row Sleep Transistor Insertion for Concurrent Clock-Gating and Power-Gating
  92. NBTI-Aware Clustered Power Gating
  93. Temperature-Insensitive Dual-$V_{\rm th}$ Synthesis for Nanometer CMOS Technologies Under Inverse Temperature Dependence
  94. Dual- assignment policies in ITD-aware synthesis
  95. Analysis of NBTI-induced SNM degradation in power-gated SRAM cells
  96. Aging effects of leakage optimizations for caches
  97. An integrated thermal estimation framework for industrial embedded platforms
  98. Dynamic indexing
  99. Generating power-hungry test programs for power-aware validation of pipelined processors
  100. On-chip Thermal Modeling Based on SPICE Simulation
  101. Reducing Timing Overhead in Simultaneously Clock-Gated and Power-Gated Designs by Placement-Aware Clustering
  102. Design of a Flexible Reactivation Cell for Safe Power-Mode Transition in Power-Gated Circuits
  103. NBTI-aware power gating for concurrent leakage and aging optimization
  104. Placement-aware clustering for integrated clock and power gating
  105. NBTI-aware sleep transistor design for reliable power-gating
  106. Thermal-Aware Design Techniques for Nanometer CMOS Circuits
  107. Ensuring temperature-insensitivity of dual-Vt designs through ITD-aware synthesis
  108. On quantifying the figures of merit of power-gating for leakage power minimization in nanometer CMOS circuits
  109. Optimal MTCMOS Reactivation Under Power Supply Noise and Performance Constraints
  110. Integrating Clock Gating and Power Gating for Combined Dynamic and Leakage Power Optimization in Digital CMOS Circuits
  111. Reducing leakage power by accounting for temperature inversion dependence in dual-Vt synthesized circuits
  112. Temperature-insensitive synthesis using multi-vt libraries
  113. Efficient Computation of Discharge Current Upper Bounds for Clustered Sleep Transistor Sizing
  114. Design of a family of sleep transistor cells for a clustered power-gating flow in 65nm technology