paiv @paiv - Tumblr Blog

Baidu Apollo

“Apollo” will provide an open, complete and reliable software platform for its partners in the automotive and autonomous driving industry to develop their own autonomous driving systems with reference vehicles and hardware platform.

#self-driving #ml #machine learning

It’s tempting to think of the mind as a layer that sits on top of more primitive cognitive structures. We experience ourselves as conscious beings, after all, in a way that feels different to the rhythm of our heartbeat or the rumblings of our sto...

The biggest distinction lies in our evolved biology, and how that biology processes information. Humans are made up of trillions of eukaryotic cells, which first appeared in the fossil record around 2.5 billion years ago.

Nature ‘has built the apparatus of rationality not just on top of the apparatus of biological regulation, but also from it and with it’, wrote the neuroscientist Antonio Damasio in Descartes’ Error (1994), his seminal book on cognition. In other words, we think with our whole body, not just with the brain.

This means that when a human approaches a new problem, most of the hard work has already been done.

#ml #machine learning #science #neuroscience #brain

Game Playing

Abstract Strategy Games

Real-time Video Games

Vision and image modelling

Image recognition

Visual Question Answering

Video recognition

Generating images

Written Language

Reading Comprehension

Language Modelling

Conversation

Translation

Spoken Language

Speech recognition

Scientific and Technical Capabilities

Solving constrained, well-specified technical problems

Reading technical papers

Solving real-world technical problems

Generating computer programs from specifications

Learning to Learn Better

Generalization

Transfer Learning

One-shot Learning

Safety and Security

"Adversarial Examples" and Manipulation of Classifiers

Safety for Reinforcement Learning Agents

Automated Hacking Systems

Pedestrian Detection for self-driving vehicles

Transparency, Explainability & Interpretability

Fairness and Debiasing

Privacy Problems

#ml #machine learning #stats

Over the last six months, a powerful new neural network playbook has come together for Natural Language Processing. The new approach can be summarised as a simple four-step formula: embed, encode, attend, predict. This post explains the components of this new approach, and shows how they're put together in two recent systems.

#ml #machine learning #nlp #classification

Back in 2004, when I had just started my career, sIFR was the hottest thing out there. It was developed by Shaun Inman and it embedded custom fonts in a small Flash movie, which coul...

What To Look For In A UI Typeface?

Legibility

Modesty

Flexibility

Large X-Height

Wide Proportions

Loose Letter Spacing

Low Stroke Contrast

OpenType Features

Fallback Fonts

Hinting

#typography #ui #ux #design

Fix dumb quotation marks and apostrophes in Swift https://github.com/frankrausch/Typographizer

#typography #apps #design #ui #ux

Competitive programming combines two topics: design of algorithms and implementation of algorithms.

#programming #contest #c++

problem-solution ordering issues

If math is the aspirin, then how do you create the headache? [1]

1: http://blog.mrmeyer.com/2015/if-math-is-the-aspirin-then-how-do-you-create-the-headache/

#education #math #gamedev

#c++#programming #security #practice

Tensorflow

tf-seq2seq is a general-purpose encoder-decoder framework for Tensorflow

[

](https://google.github.io/seq2seq/)

#neural networks #nn #translation #tensorflow #stats #math

What's the ground truth on artificial intelligence (AI)? In this video, John Launchbury, the Director of DARPA's Information Innovation Office (I2O), attempt...

Three waves of AI

Handcrafted Knowledge

Statistical Learning

Contextual Adaptation

AI attributes

perceiving

learning

abstracting

reasoning

#ai #artificial intelligence #science #stats

A visual introduction to probability and statistics.

Basic Probability

Likelihood

Expectation

Estimation

Compound Probability

Set Theory

Combinatorics

Conditional Probability

Distributions

Random Variable

Discrete and Continuous

Central Limit Theorem

Statistical Inference

Confidence Intervals

p-Values

Hypothesis Testing

Linear Regression

Ordinary Least Square

Correlation

Analysis of Variance

#statistics #stats #visualization #interactive #math

We give an overview of recent exciting achievements of deep reinforcement learning (RL). We start with background of deep learning and reinforcement learning, as well as introduction of testbeds. Next we discuss Deep Q-Network (DQN) and its extensions, asynchronous methods, policy optimization, reward, and planning. After that, we talk about attention and memory, unsupervised learning, and learning to learn. Then we discuss various applications of RL, including games, in particular, AlphaGo, robotics, spoken dialogue systems (a.k.a. chatbot), machine translation, text sequence prediction, neural architecture design, personalized web services, healthcare, finance, and music generation.

#ml #machine learning #neural networks