Functional Magnetic Resonance Imaging (fMRI) is an advanced neuroimaging method that enables in-depth analysis of brain activity by measuring dynamic changes in the blood oxygenation level-dependent (BOLD) signals. However, the resource-intensive nature of fMRI data acquisition limits the availability of high-fidelity samples required for data-driven brain analysis models. While modern generative models can synthesize fMRI data, they often underperform because they overlook the complex non-stationarity and nonlinear BOLD dynamics. To address these challenges, we introduce T2I-Diff, an fMRI generation framework that leverages time-frequency representation of BOLD signals and classifier-free denoising diffusion. Specifically, our framework first converts BOLD signals into windowed spectrograms via a time-dependent Fourier transform, capturing both the underlying temporal dynamics and spectral evolution. Subsequently, a classifier-free diffusion model is trained to generate class-conditioned frequency spectrograms, which are then reverted to BOLD signals via inverse Fourier transforms. Finally, we validate the efficacy of our approach by demonstrating improved accuracy and generalization in downstream fMRI-based brain network classification. The code is available at repository Keywords: fMRI Time-Frequency Image Diffusion Models.

It has been quite a year for legal tech startup Evisort. Twelve months ago this week, the company introduced its flagship product, Document Analyzer, a cloud-based AI and text-mining application that helps enterprises analyze and manage their contracts. At the time, I wrote that it "might just be the hottest legal tech and AI company you've never heard of." After launching with angel funding from Amity Ventures, an early-stage venture capital firm, and Village Global, a VC firm whose backers include Bill Gates, Mark Zuckerberg, Jeff Bezos and Reid Hoffman, the company earlier this year raised another $4.5 million in seed funding. Now today it is announcing that it has closed a Series A funding round of $15 million.

A recent proposal of data dependent similarity called Isolation Kernel/Similarity has enabled SVM to produce better classification accuracy. We identify shortcomings of using a tree method to implement Isolation Similarity; and propose a nearest neighbour method instead. We formally prove the characteristic of Isolation Similarity with the use of the proposed method. The impact of Isolation Similarity on density-based clustering is studied here. We show for the first time that the clustering performance of the classic density-based clustering algorithm DBSCAN can be significantly uplifted to surpass that of the recent density-peak clustering algorithm DP. This is achieved by simply replacing the distance measure with the proposed nearest-neighbour-induced Isolation Similarity in DBSCAN, leaving the rest of the procedure unchanged. A new type of clusters called mass-connected clusters is formally defined. We show that DBSCAN, which detects density-connected clusters, becomes one which detects mass-connected clusters, when the distance measure is replaced with the proposed similarity. We also provide the condition under which mass-connected clusters can be detected, while density-connected clusters cannot.

Four Harvard Law students have their heads in the cloud--and they think the rest of the legal profession should join them. With their powerful new search engine called Evisort that harnesses cloud storage and artificial intelligence, they hope to revolutionize the costly and labor-intensive way that lawyers currently handle contracts and other transactional work, liberating them for more creative and interesting tasks. Developed by the students over the past two years, Evisort is "like Google for legal contracts," says Jerry Ting '18, co-founder and CEO, who came up with the idea as an undergraduate. While artificial intelligence is the cutting-edge of automating labor-intensive tasks such as document review, it hasn't yet been widely applied to contracts. Evisort jumps into that gap by enabling lawyers to quickly sort through thousands of contracts and other documents to unlock key insights for transactional work.

At the beginning of the year, efforts to put driverless cars on California's streets looked like they were careening. Uber had defied state officials by failing to get permits to test its technology and then the company shipped its cars to Arizona to test them there. After four years of trying, regulators were still trying to write rules for testing cars without anyone in the driver's seat. Lawmakers and tech industry representatives worried that California was losing its grip on innovation in a sector primed for growth. Now, after this year's release of guidelines from the state Department of Motor Vehicles, the mood has changed.

For patients with epilepsy, or cancerous brain lesions, sometimes the only way to forward is down. Down past the scalp and into the skull, down through healthy grey matter to get at a tumor or the overactive network causing seizures. At the end of the surgery, all that extra white and grey matter gets tossed in the trash or an incinerator. For the last few years, doctors at a number of hospitals in the Emerald City have been saving those little bits and blobs of brain, sticking them on ice, and rushing them off in a white van across town to the Allen Institute for Brain Science. Scientists there have been keeping the tissue on life support long enough to tease out how individual neurons look, act, and communicate.

When you throw an event hoping to draw 400 people but an audience of 29,000 shows up, do you think it's a good sign indicating you're onto something? That incredible interest is what happened in Beijing the week of 28 November 2016 at the International Summit on Machine Learning and Industry Application. The event's 20 speakers gathered from across industries and academia to offer their insights about machine learning trends and new directions. For the keynote address, Dinesh Nirmal, vice president, analytics development, at IBM, teamed up with Kent Ting, vice president, IBM Analytics Global Consulting Group, at IBM. Nirmal and Ting talked about the IBM focus on machine learning and the company's efforts to enable developers in China and elsewhere. Of particular interest to the audience was their demo of IBM Watson Machine Learning, a full-service IBM Bluemix platform offering.

Binary is the story of a man who must decide between saving his artificially intelligent girlfriend or a human woman during a crucial space voyage, causing him to question what love really means. Binary will be a 20-minute, live-action short film. Ryker - Loyal and naive, Ryker grew up in the working class. When he falls in love with an artificially intelligent woman, Seline, he struggles with whether to prioritize his love or his fellow human. Seline - An advanced form of artificial intelligence, appearing human, Seline has been programmed with the capacity to love. She must convince Ryker and Natalie her love is as valuable as human love.