Variational ab-initio methods in quantum chemistry stand out among other methods in providing direct access to the wave function. This allows in principle straightforward extraction of any other observable of interest, besides the energy, but in practice this extraction is often technically difficult and computationally impractical. Here, we consider the electron density as a central observable in quantum chemistry and introduce a novel method to obtain accurate densities from real-space many-electron wave functions by representing the density with a neural network that captures known asymptotic properties and is trained from the wave function by score matching and noise-contrastive estimation. We use variational quantum Monte Carlo with deep-learning ans\"atze (deep QMC) to obtain highly accurate wave functions free of basis set errors, and from them, using our novel method, correspondingly accurate electron densities, which we demonstrate by calculating dipole moments, nuclear forces, contact densities, and other density-based properties.

De Groot was going on a year long trip to the U.S. and the highlight of his journey was a visit to Herb Simon and Allen Newell. I met Allen for the first time when I came for a two semester long visit to Carnegie Mellon University in 1968. This encounter was a distinct factor in my later decision to join the faculty at Carnegie Mellon University. I interacted with Allen much more closely when I became department head in 1979. He was for me a mentor and a sounding board for ideas I wanted to pursue for computer science at Carnegie Mellon University. I enjoyed working with many good friends on the faculty, but Allen was really special. Many of us will remember him for his evenhanded treatment of all students at the Black Friday meetings. He would never pursue his own agenda, he would always look for the merit of a student's work and not whether the rules were violated. He was a staunch defender of the rule that replaces all rules, which says that the only thing that counts is whether or ...

I am pleased to present this issue, most of which is devoted to a single subject-Spatial Reasoning. Our guest editor is Avi Kak, of Purdue University. Avi called me in the Summer of 1987, very enthused about a workshop he had recently attended. The idea of a "theme issue" on spatial reasoning sounded like a winner to me. I asked Avi to take the responsibility for selecting and editing the articles, and he agreed.

AAAI has supported small workshops for the last several years. This support has included publicity, printing, office help, and subsidies for other expenses. Typical grants have been $5,000.00, Any topic in AI science or technology is appropriate, and anyone may volunteer to organize a workshop on any topic. The organizer(s) should determine the topic, the date, the site, and the procedure for selecting papers and attendees.

I met Allen for the first time when I came for a two semester long visit to Carnegie Mellon University in 1968. This encounter was a distinct factor in my later decision to join the faculty at Carnegie Mellon University.

Good books, well conceived, well written, and well presented, can do much to promote the science of AI and the AAAI organization. The AAAI Press edited collections, from which the articles of this issue are excerpted, are designed to reach out to an audience that wants to learn more about AAAI and AI.

I agree with much of what Dr. Levinson has to say, especially

Our guest editor is Avi Kak, of Purdue University. We also round out the issue with the final installment of Steven Frank's Swartout, on an AAAIsponsored Planning Workshop, held last year. "open-ended" (i.e., almost any aspect of the experienced world might be Book reviews should be submitted to the Book Review Editor, Bruce D'Ambrosio, Computer Science Department, Oregon State University, Corvallis, OR 97331 (503) 754.4466 Advertising rates and media kits are available upon request from AI Magazine, 445 Burgess Drive, Menlo Park, CA 94025 Telephone (415) 328.3123

Ms. Claudia Mazzetti AAAI AAAI has supported small workshops for the last several years. This support has 445 Burgess Drive included publicity, printing, office help, and subsidies for other expenses. Any topic in AI science or technology is appropriate, and anyone may volunteer Submit all proposals to: to organize a workshop on any topic. The organizer(s) should determine Jay M. Tenenbaum, Chair, AAAI Conference the topic, the date, the site, and the procedure for selecting papers and attendees. Committee He or she should also decide whether preprints should be distributed.

This support has in-Intelligence will be held 13-17 July 1987 in M. Tenenbaum, Chair; Ronald Brachman,:luded publicity, printing, office help, and Seattle, Washington. Typical grants AAAI-87's Technical Program will from the membership for conference iave been $5,000, although requests for up present outstanding research papers in AI. sites for 1988, 1990, and 1991. The proposal to $10,000 will be considered. Any topic in These papers will be divided into those emphasizing should be structured around the new AI science or technology is appropriate, basic research and those emphasizing five day format described elsewhere in this and anyone may volunteer to organize a applied research. Based on a predictive workshop on any topic.