Martin Gorner
where else to find them
what they talk about
all 7 in the filters
where they keep going back
- Google I/O2 editions2019–2021
all 6 in the filters
on a stage with
- Francois Cholletonce
- Kaz Satoonce
who talks about the same things
- Sara Robinson17 talks
- Yufeng Guo8 talks
- Robert Crowe12 talks
- Josh Gordon10 talks
- Ronen Dar3 talks
- Barbara Fusinska10 talks
| title | conference | date |
|---|---|---|
| Demo: Building a Gemma chatbot with Keras | Gemma Developer Day 2024 | 2024-03-07 |
Shows how to load Gemma Instruct 7b from the Keras NLP collection / Kaggle Model Hub with a one‑liner, use turn‑by‑turn tagging and feed the full conversation… | ||
| Modern Keras Design Patterns | Google I/O 2021 | 2021-05-18 |
Builds a variational autoencoder in Keras and shows the concrete changes needed: adds a sampling layer that returns z sampled from z_mean and z_log_var, uses… | ||
| Cloud TPU Pods: AI Supercomputing for Large Machine Learning Problems | Google I/O 2019 | 2019-05-07 |
Cloud TPUs use a custom bfloat16 format and a 128x128 systolic array to pack many 16-bit multiply‑accumulators into efficient chips; TPU v2 pods reach 11.6… | ||
| Tensorflow, deep learning and modern RNN architectures, without a PhD | Devoxx Belgium 2017 | 2017-11-06 |
Walks through building working systems with concrete choices: TensorFlow dynamic_rnn plus GRU cells, bi‑directional RNNs, and GloVe embeddings; attention is… | ||
| Tensorflow and deep reinforcement learning, without a PhD | Devoxx Belgium 2017 | 2017-11-06 |
Trains a policy-gradient agent in TensorFlow to play Pong from raw pixels using frame differences, a tiny two-layer dense network and sampling of actions via… | ||
| Tensorflow, deep learning and modern convolutional neural nets, without a PhD | Devoxx Belgium 2017 | 2017-11-06 |
Builds a plane detector starting from a 20x20 classifier trained in TensorFlow + ML Engine using TensorBoard, the Estimator API and the Dataset API; converts… | ||
| Interview with Martin Görner | Devoxx Belgium 2017 | 2017-11-06 |
TensorFlow is presented as a researcher-grade Python library designed to be production-ready, now with TensorFlow 1.4 and higher-level APIs that make model… | ||
| Serverless datastream processing | Devoxx Belgium 2017 | 2017-11-06 |
End-to-end serverless ad‑serving pipeline for connected NYC taxis built on Google Cloud: ingest via Pub/Sub at ~10,000 events/sec, stream-transform and… | ||
| TensorFlow and Deep Learning without a PhD, Part 1 | Google Cloud Next '17 | 2017-03-08 |
Builds an MNIST digit recognizer in TensorFlow that moves from a single-layer softmax baseline (92% accuracy) to a deep model with relu activations… | ||
| Cloud Dataflow and the FlumeJava Paper Explained | DevFest Paris 2015 | 2015-01-30 |
Argues that MapReduce is outdated and presents Flume and MillWheel as the foundations for a unified batch-and-stream model implemented as Cloud Dataflow… | ||
| 'No One at Google Uses MapReduce Anymore' - Cloud Dataflow | DevFest Nantes 2014 | 2014-11-07 |
Explains Google's move beyond MapReduce to newer models—Flume for pipeline definition and MillWheel for real-time dataflow—and introduces Cloud Dataflow, a… | ||
| nothing matches | ||