Skip to main navigation
Skip to search
Skip to main content
New Jersey Institute of Technology Home
Help & FAQ
Home
Profiles
Research units
Facilities
Federal Grants
Research output
Press/Media
Search by expertise, name or affiliation
Mixed-Precision Deep Learning Based on Computational Memory
S. R. Nandakumar
, Manuel Le Gallo
, Christophe Piveteau
, Vinay Joshi
, Giovanni Mariani
, Irem Boybat
, Geethan Karunaratne
, Riduan Khaddam-Aljameh
, Urs Egger
, Anastasios Petropoulos
, Theodore Antonakopoulos
, Bipin Rajendran
, Abu Sebastian
, Evangelos Eleftheriou
Research output
:
Contribution to journal
›
Article
›
peer-review
89
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Mixed-Precision Deep Learning Based on Computational Memory'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Computational Memory
100%
Deep Learning Methods
100%
Phase Change Random Access Memory (PCRAM)
100%
Mixed Precision
100%
Deep Neural Network
66%
Memory Unit
66%
Multilayer Perceptron
66%
Weighted Sums
66%
Conductance States
66%
Weight Update
66%
Hardware Complexity
33%
Energy Efficiency
33%
Cognitive Task
33%
Image Recognition
33%
System Level
33%
Conductance
33%
Postsynaptic Density Protein 95 (PSD-95)
33%
Fundamental Challenges
33%
Proposed Architecture
33%
Computationally Intensive
33%
Artificial Intelligence
33%
Software Training
33%
Processing Unit
33%
Generative Adversarial Networks
33%
Convolutional Neural Network
33%
Behavioral Model
33%
Update Mechanism
33%
Non-ideality
33%
32-bit
33%
MNIST
33%
Non-von Neumann
33%
Floating-point
33%
Digital Processing
33%
Handwritten Digits
33%
Crossbar Array
33%
Novel Architectures
33%
Speech Recognition
33%
Resistive Memory Devices
33%
Memory Network
33%
Test Accuracy
33%
Memory Array
33%
Training Accuracy
33%
Fully Digital
33%
Training Experiment
33%
Computer Science
Deep Learning
100%
Deep Neural Network
100%
Multilayer Perceptron
100%
Energy Efficiency
50%
Artificial Intelligence
50%
Computer Architecture
50%
Processing Unit
50%
And-States
50%
Generative Adversarial Networks
50%
Convolutional Neural Network
50%
Floating Point
50%
Point Implementation
50%
handwritten digit
50%
Synaptic Weight
50%
Speech Recognition
50%
Resistive Memory
50%
Long Short-Term Memory Networks
50%
Software Training
50%
Memory Array
50%
Bit Implementation
50%
Neuroscience
Neural Network
100%
Perceptron
66%
Short-Term Memory
33%
Speech Recognition
33%
Digital Processing
33%
Material Science
Phase-Change Memory
100%
Digital Processing
33%