smalltalk


Object Detection with TensorFlow and Smalltalk

#artificialintelligence

In a previous post we saw basic object recognition in images using Google's TensorFlow library from Smalltalk. This post will walk you step by step through the process of using a pre-trained model to detect objects in an image. It may also catch your attention that we are doing this from VASmalltalk rather than Python. Check out the previous post to see why I believe Smalltalk could be a great choice for doing Machine Learning. We provide a collection of detection models pre-trained on the COCO dataset, the Kitti dataset, the Open Images dataset, the AVA v2.1 dataset and the iNaturalist Species Detection Dataset.


Recognizing objects in images with TensorFlow and Smalltalk

#artificialintelligence

In this post, I will be showing a simple example of object recognition in images using the TensorFlow library from Smalltalk. Whenever you start entering the world of AI and Machine Learning you will notice immediately that Python has been widely accepted as the "default" programming language for these topics. I am not against Python and I believe that people are using it for a reason. However, I do believe that providing alternatives is a good thing, too. And Smalltalk could be that alternative you are looking for.


CobotDS: A Spoken Dialogue System for Chat

AAAI Conferences

We describe CobotDS, a spoken dialogue system providing access to a well-known internet chat server called LambdaMOO. CobotDS provides real-time, two-way, natural language communication between a phone user and the multiple users in the text environment. We describe a number of the challenging design issues we faced, and our use of summarization, social filtering and personalized grammars in tackling them. We report a number of empirical findings from a small user study.


AAAI82-056.pdf

AAAI Conferences

Smalltalk classes may be arranged in hierarchies, so that a class can inherit the properties of another class. In the standard Smalltalk language, a class may inherit from only one other class. In this paper we describe an implementation of multiple inheritance in Smalltalk.


DESCRIPTIONS FOR A PROGRAMMING ENVIRONMENT

AAAI Conferences

U.S.A Abstract PIE is an experimental personal information environment implemented in Smalltalk that uses a description language to support the interactive development of programs. PIE contains a network of nodes, each of which can be assigned several perspectives. Each perspective describes a different aspect of the program structure represented by the node, and provides specialized actions from that point of view. Contracts can be created that monitor nodes describing different parts of a program's description. Contractual agreements are expressible as formal constraints, or, to make the system failsoft, as English text interpretable by the user. Contexts and layers are used to represent alternative designs for programs described in the network.