tensorflow   6658

« earlier    

Google AI Blog: MorphNet: Towards Faster and Smaller Neural Networks
Deep neural networks (DNNs) have demonstrated remarkable effectiveness in solving hard problems of practical relevance such as image classification, text recognition and speech transcription. However, designing a suitable DNN architecture for a given problem continues to be a challenging task. Given the large search space of possible architectures, designing a network from scratch for your specific application can be prohibitively expensive in terms of computational resources and time. Approaches such as Neural Architecture Search and AdaNet use machine learning to search the design space in order to find improved architectures. An alternative is to take an existing architecture for a similar problem and, in one shot, optimize it for the task at hand.

Here we describe MorphNet, a sophisticated technique for neural network model refinement, which takes the latter approach. Originally presented in our paper, “MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks”, MorphNet takes an existing neural network as input and produces a new neural network that is smaller, faster, and yields better performance tailored to a new problem. We've applied the technique to Google-scale problems to design production-serving networks that are both smaller and more accurate, and now we have open sourced the TensorFlow implementation of MorphNet to the community so that you can use it to make your models more efficient.
machine_learning  TensorFlow 
yesterday by amy
What Machine Learning needs from Hardware « Pete Warden's blog
Photo by Kimberly D On Monday I'll be giving a keynote at the IEEE Custom Integrated Circuits Conference, which is quite surprising even to me, considering I'm a software engineer who can barely solder! Despite that, I knew exactly what I wanted to talk about when I was offered the invitation. If I have a…
hardware  machine.learning  future  design  software  neural.networks  tensorflow 
3 days ago by po
Will Compression Be Machine Learning’s Killer App? « Pete Warden's blog
Photo by Greg Simenoff When I talk to people about machine learning on phones and devices I often get asked "What's the killer application?". I have a lot of different answers, everything from voice interfaces to entirely new ways of using sensor data, but the one I'm most excited about in the near-team is compression.…
machine.learning  compression  interesting  deep.learning  tensorflow 
3 days ago by po
Pete Warden's blog
Ever tried. Ever failed. No matter. Try Again. Fail again. Fail better.
blogs  machine.learning  ai  deep.learning  research  technical  tensorflow 
3 days ago by po
zzh8829/yolov3-tf2: YoloV3 Implemented in Tensorflow 2.0
YoloV3 Implemented in Tensorflow 2.0. Contribute to zzh8829/yolov3-tf2 development by creating an account on GitHub.
yolo  object-detection  tensorflow  deep-learning 
3 days ago by pmigdal

« earlier    

related tags

ai  alternativas  api  apple  arduino  article  artificialintelligence  avro  aws  bi  blogs  causal  compilers  compression  course  cucumber  custom  data-science  data-visualization  data  dataengineering  datascience  deep-learning-compiler  deep-learning  deep.learning  deeplearning  deployment  design  detection  devconmu  dl  docker  education  eks  embedded  esp8266  explainer  filter  flask  forecasting  frameworks  future  generative  github  golang  google  hardware  hn  hub  ia  image-classification  interesting  ios  iot  japan  javascript  jetsonnano  jupyter  jvm  k8s  kaggle  keras  kubeflow  kubernetes  learning  legos  library  lightgbm  list  llvm  machine-learning  machine.learning  machine  machine_learning  machinelearn  machinelearning  ml  models  mscc  music  mxnet  network  neural-network  neural.networks  neural  neuralnets  nlp  no-code  nodejs  nvidia  object-detection  object  open-source  papers  people  performance  predictions  probability  programming  python  pytorch  raspberrypi  research  resource  resume  rust  scala  scikit-learn  semantics  software  statistics  stocks  swift  switch  tech  technical  tensor  tensorrt  tf  tfp  tfserving  time_series  timeseries  tm358  todo:interarma  tpu  tutorial  uber-oss  uber  ubuntu  video  visualization  voice  xgboost  yolo 

Copy this bookmark:



description:


tags: