4 code implementations • 1 Mar 2017 • Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Dan Fink, Olivier Francon, Bala Raju, Hormoz Shahrzad, Arshak Navruzyan, Nigel Duffy, Babak Hodjat
The success of deep learning depends on finding an architecture to fit the task.
no code implementations • 10 Mar 2018 • Jason Liang, Elliot Meyerson, Risto Miikkulainen
Multitask learning, i. e. learning several tasks at once with the same neural network, can improve performance in each of the tasks.
1 code implementation • 18 Feb 2019 • Jason Liang, Elliot Meyerson, Babak Hodjat, Dan Fink, Karl Mutch, Risto Miikkulainen
However, the success of DNNs depends on the proper configuration of its architecture and hyperparameters.
no code implementations • 11 Feb 2020 • Jason Liang, Santiago Gonzalez, Hormoz Shahrzad, Risto Miikkulainen
This paper presents an algorithm called Evolutionary Population-Based Training (EPBT) that interleaves the training of a DNN's weights with the metalearning of loss functions.
no code implementations • 16 Feb 2021 • Jason Liang, Keith Kelly
We implement stacked denoising autoencoders, a class of neural networks that are capable of learning powerful representations of high dimensional data.
no code implementations • NeurIPS 2021 • Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Deepta Rajan, Jason Liang, Akshay Chaudhari, Andreas Spanias
Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models.
1 code implementation • 23 Jun 2022 • Hendrik Borras, Giuseppe Di Guglielmo, Javier Duarte, Nicolò Ghielmetti, Ben Hawks, Scott Hauck, Shih-Chieh Hsu, Ryan Kastner, Jason Liang, Andres Meza, Jules Muhizi, Tai Nguyen, Rushil Roy, Nhan Tran, Yaman Umuroglu, Olivia Weng, Aidan Yokuda, Michaela Blott
We present our development experience and recent results for the MLPerf Tiny Inference Benchmark on field-programmable gate array (FPGA) platforms.
no code implementations • 8 Aug 2023 • Jason Liang, Hormoz Shahrzad, Risto Miikkulainen
Next, it was evaluated in 11-bit multiplexer design (a single-population discovery task with extended variability), where a 14-fold speedup was observed.