Feb 25

Build Your Own Autonomous Vehicle

So you decided to build build your own self-driving AV car ? Where would you start, how much would it cost, how to do it ? What is available out there so you don’t have to start from scratch ? Major AV stacks are comma.ai, Baidu Apollo¹, Autoware, Nvidia Drive. …

Autonomous Cars

2 min read

Jan 15

Self-driving Cars — The Current State of Affairs

Self-driving cars are quite important AI/robotics application because of the staggering human and material cost of traffic accidents, huge commercial potential ( insurance costs ) and the fact that modern vehicles are ready-made, functional robot actuator hardware ( no messy limbs/grippers, stair climbing or door knobs to deal with; very…

Autonomous Vehicles

2 min read

Jan 9, 2021

Learning and Acting in Unknown Environments

Jurgen Schmidhuber’s 1990 Reinforcement Learning and Planning based on an agent consisting of a controller C and a world model M¹ is a great and widely applicable concept that found its latest implementation in DeepMind’s muZero² project. M learns to predict the consequences of C’s actions. C learns to use…

12 min read

Learning and Acting in Unknown Environments

Oct 27, 2020

Tesla Full Self Driving Beta Rollout

What is the technology and algorithm behind the Tesla FSD Beta release ? According to Tesla’s AI Director Andrey Karpathy the technique is Imitation Learning: While you are driving a car what you’re actually doing is you are entering the data because you are steering the wheel. You’re telling us…

3 min read

Tesla Full Self Driving Beta Rollout — Imitation Learning

Sep 12, 2020

Risk.Net Machine Learning in Finance Course: Neural nets and Reinforcement Learning

I presented at http://Risk.Net Machine Learning in Finance Course: Neural Nets and Reinforcement Learning ( Day 3 ) https://training.risk.net/machine-learning/event-agenda Slides Many thanks to the organizers, Lucy Taylor and Fenella Murray from Infopro Digital. Some surprising course poll results: most of the attendees do not use NLP in their organizations. 30% use ML for credit scoring. Some not so surprising results: nobody expects self-driving cars in the next five years.

1 min read

Risk.Net Machine Learning in Finance Course: Neural nets and Reinforcement Learning

I presented at http://Risk.Net Machine Learning in Finance Course: Neural Nets and Reinforcement Learning ( Day 3 ) https://training.risk.net/machine-learning/event-agenda

Slides

Many thanks to the organizers, Lucy Taylor and Fenella Murray from Infopro Digital.

Some surprising course poll results: most of the attendees do not use NLP in their organizations. 30% use ML for credit scoring.

Some not so surprising results: nobody expects self-driving cars in the next five years.

May 20, 2020

Reinforcement Learning For Real Life: Contextual Bandits

RL is not really a solved area and particularly there are very simple problems which will break it .

Reinforcement Learning

4 min read

Jan 18, 2020

Reformer: The Efficient Transformer

Today, we introduce the Reformer, a Transformer model designed to handle context windows of up to 1 million words, all on a single accelerator and using only 16GB of memory. When Transformer was announced back in 2017, it created a major shift in NLP towards large language models. Transformer based…

Machine Learning

2 min read

Jul 4, 2019

LSTM Primer With Real Life Application ( DeepMind Continuous Risk Model of Acute Kidney Injury Prediction from EHR)*

LSTM is the key algorithm that enabled major ML successes like Google speech recognition and Translate¹. It was invented in 1997 by Hochreiter and Schmidhuber as an improvement over RNN vanishing/exploding gradient problem. LSTM can be used to model many types of sequential data² — from time series data to…

Machine Learning

11 min read

Nov 5, 2018

Google BERT — Pre Training and Fine Tuning for NLP Tasks

A recently released BERT paper and code generated a lot of excitement in ML/NLP community¹. BERT is a method of pre-training language representations, meaning that we train a general-purpose “language understanding” model on a large text corpus ( BooksCorpus and Wikipedia), and then use that model for downstream NLP tasks…

Machine Learning

7 min read

Oct 10, 2018

Deep Learning Stack — Algos, TensorFlow, PyTorch, Kubernetes, TPU, GPU, FPGA

A whole new software ( TensorFlow, PyTorch, Kubernetes¹) and hardware¹³ ( TPU, GPU, FPGA ) stack⁹ is being built or put together around the needs of Machine Learning community¹⁰ ¹². TensorFlow created that whole weird signal² , followed by PyTorch and other frameworks. In short order we’ve seen the merge…

Machine Learning

4 min read

Build Your Own Autonomous Vehicle

Self-driving Cars — The Current State of Affairs

Learning and Acting in Unknown Environments

Tesla Full Self Driving Beta Rollout

Risk.Net Machine Learning in Finance Course: Neural nets and Reinforcement Learning

Risk.Net Machine Learning in Finance Course: Neural nets and Reinforcement Learning

Reinforcement Learning For Real Life: Contextual Bandits

Reformer: The Efficient Transformer

LSTM Primer With Real Life Application ( DeepMind Continuous Risk Model of Acute Kidney Injury Prediction from EHR)*

Google BERT — Pre Training and Fine Tuning for NLP Tasks

Deep Learning Stack — Algos, TensorFlow, PyTorch, Kubernetes, TPU, GPU, FPGA

Ranko Mosic